Japanese and Korean voice search
The DOI matches its Crossref record; 7 of the 8 references it cites were found in a registry or an index.
Abstract
This paper describes challenges and solutions for building a successful voice search system as applied to Japanese and Korean at Google. We describe the techniques used to deal with an infinite vocabulary, how modeling completely in the written domain for language model and dictionary can avoid some system complexity, and how we built dictionaries, language and acoustic models in this framework. We show how to deal with the difficulty of scoring results for multiple script languages because of ambiguities. The development of voice search for these languages led to a significant simplification of the original process to build a system for any new language which in in parts became our default process for internationalization of voice search.
Overview
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
In the citing paper
“LogRobust [8], which encodes log templates into semantic vectors using the FastText pre-trained model [31], cannot work well on 2 out of 4 datasets.”
From Log-based Anomaly Detection Without Log Parsing (2021) · cites this paper as [8]
In the citing paper
“Their empirical study on a Microsoft online service system shows that up to 30.3% logs are changed in the latest version.”
From Log-based Anomaly Detection Without Log Parsing (2021) · cites this paper as [8]
In the citing paper
“Zhang et al. [8] indicated that log data is unstable, meaning that new log events often appear due to software evolution at its lifetime.”
From Log-based Anomaly Detection Without Log Parsing (2021) · cites this paper as [8]
In the citing paper
“Another option is to use domain knowledge to reduce the input space of a model — such strategies include patch embeddings [Dosovitskiy et al. 2020] as well as fixed or learned tokenization [Schuster and Nakajima 2012; Sennrich et al. 2016; Kudo and Richardson 2018; van den Oord et al. 2017; Ramesh et al. 2021]. These methods may alleviate some challenges facing generative approaches, but have the”
From On the Opportunities and Risks of Foundation Models (2021) · cites this paper as Schuster and Nakajima 2012
Citations
Cites
Semi-tied covariance matrices for hidden Markov models
Gales, M. J. F. (1999) · IEEE Transactions on Speech and Audio Processing · doi:10.1109/89.759034 · Cited by 537
Boosted MMI for model and feature-space discriminative training
Povey, D., Kanevsky, D., Kingsbury, B., Ramabhadran, B., Saon, G., & Visweswariah, K. (2008) · 2008 IEEE International Conference on Acoustics, Speech and Signal Processing · doi:10.1109/icassp.2008.4518545 · Cited by 341
“Your Word is my Command”: Google Search by Voice: A Case Study
Schalkwyk, J., Beeferman, D., Beaufays, F., Byrne, B., Chelba, C., Cohen, M., Kamvar, M., & Strope, B. (2010) · Advances in Speech Recognition · doi:10.1007/978-1-4419-5951-5_4 · Cited by 232
Building transcribed speech corpora quickly and cheaply for many languages
Hughes, T., Nakajima, K., Ha, L., Vasu, A., Moreno, P. J., & LeBeau, M. (2010) · Interspeech (USB) · doi:10.21437/interspeech.2010-551 · Cited by 75
Self-citationGoogle Search by Voice: A Case Study
Schalkwyk, J., Beeferman, D., Beaufays, F., Byrne, B., Chelba, C. I., Cohen, M., Garrett, M., & Strope, B. P. (2010) · Cited by 63
Query language modeling for voice search
Chelba, C. I., Schalkwyk, J., Brants, T., Ha, V., Harb, B., Neveitt, W., Parada, C., & Xu, P. (2010) · IEEE Spoken Language Technology Workshop (SLT) · doi:10.1109/slt.2010.5700834 · Cited by 28
Search by voice in Mandarin Chinese
Shan, J., Wu, G., Hu, Z., Tang, X., Jansche, M., & Moreno, P. J. (2010) · Interspeech (USB) · doi:10.21437/interspeech.2010-129 · Cited by 18
Research works printed but not linked: 1
- sung, 0, Deploying Search by Voice in Cantonese, Proc Interspeech 2011
Cited by
Items 801–900 of 933
Authorship attribution of small messages
Júnior, A. C. T. C. (2022) · doi:10.47749/t/unicamp.2022.1254885
Character-Level Chinese Backpack Language Models
Sun, H., & Hewitt, J. (2023) · BlackboxNLP Workshop on Analyzing and Interpreting Neural Networks for NLP (BlackboxNLP) · doi:10.18653/v1/2023.blackboxnlp-1.8 · Cited by 2
Bridging the Gap between Subword and Character Segmentation in Pretrained Language Models
Kiyono, S., Takase, S., Li, S., & Sato, T. (2023) · International conference Recent advances in natural language processing · doi:10.26615/978-954-452-092-2_062 · Cited by 1
Pareto Efficiency of Learning-Forgetting Trade-Off in Neural Language Model Adaptation
Bellegarda, J. R. (2023) · IEEE Workshop on Automatic Speech Recognition and Understanding (ASRU) · doi:10.1109/asru57964.2023.10389713
“We therefore opt to train on only 4B tokens worth of generic data, where here a token is a sub-word unit obtained using the “sentence piece” approach [30] with a total lexicon of about 25K distinct tokens.”
MethodExtracting Visual Semantic Information for Solving Visual Question Answering
Huang, Y. (2023) · IEEE International Conference on Data Science and Computer Application (ICDSCA) · doi:10.1109/icdsca59871.2023.10393030
“From GRiT[11] through the WordPiece [9, 12]model using text markup to record every word, and not only confined to the simple classification of nouns, he also can produce some complex descriptive sentences, And it can generate various tasks into a unified framework.”
MethodMultilingual Question Answering Applied to Conversational Agents
Siblini, W., Pasqual, C., Lavielle, A., Challal, M., & Cauchois, C. (2024) · Studies in computational intelligence · doi:10.1007/978-3-031-40403-0_5
Le traitement automatique des langues face à l'évolution des usages de la langue
Grouin, C. (2023) · HAL
An Efficient Method To Accelerate Rnn-T Decoding For Asr
Zhao, Y., Wu, R., Fang, R., Yin, J., Lin, J., Huang, H., Li, R., Huang, W., & Mao, Y. (2023) · International Conference on Digital Society and Intelligent Systems (DSInS) · doi:10.1109/dsins60115.2023.10455601
“End-to-end (E2E) modeling for automatic speech recognition (ASR) predicts word or wordpiece [1] sequences directly from the acoustic sequences, which simplifies both training and decoding process, compared with the conventional ASR system such as DNN-HMM.”
MethodSong, H., Mao, Z., Dabre, R., Chu, C., & Kurohashi, S. (2024) · Journal of Natural Language Processing · doi:10.5715/jnlp.31.155
Acceleration of automatic speech recognition for low-power devices
Rivero, D. P. (2022) · UPCommons institutional repository (Universitat Politècnica de Catalunya) · doi:10.5821/dissertation-2117-404658 · Cited by 1
Valencia, R. B., & Recario, R. N. C. (2024) · Lecture notes in networks and systems · doi:10.1007/978-3-031-53960-2_33
Cross-lingual Information Extraction for the Assessment and Prevention of Adverse Drug Reactions
Raithel, L. (2024) · theses.fr (ABES) · doi:10.70675/5478ceccz18cdz4fcbzb106z2fb1ec257de2 · Cited by 3
Chung, P., Fong, C. T., Walters, A. M., Yetişgen, M., & O’Reilly-Shah, V. N. (2023) · Figshare · doi:10.6084/m9.figshare.24089264
Intelligent Natural Language Processing for Epidemic Intelligence
Croce, D., Borazio, F., Gambosi, G., Basili, R., Margiotta, D., Scaiella, A., Manso, M. D., Petrone, D., Cannone, A., Mateo‐Urdiales, A., et al. (2023) · Italian Journal of Computational Linguistics · doi:10.4000/ijcol.1250
A Large Financial Chat ModelPreprint
Ding, F. (2024) · doi:10.33774/coe-2024-lsc94
Joint embedding of graph-guided features for radiology report summarization
Sun, D., Xuyang, F., Bin, L., & Ding, Z. (2024) · International Conference on Image, Signal Processing and Pattern Recognition (ISPP) · doi:10.1117/12.3033815
Nugues, P. (2024) · Cognitive technologies · doi:10.1007/978-3-031-57549-5_13
de Madrid, U. C., García-Sierra, Ó., Cesteros, A. M. F., de Madrid, U. C., Ortega-Martín, M., & de Madrid, U. C. (2024) · Revista Española de Lingüística · doi:10.31810/rsel.54.1.4
BELMASK—An Audiovisual Dataset of Adversely Produced Speech for Auditory Cognition Research
Moshona, C. C., Rudawski, F., Fiebig, A., & Sarradj, E. (2024) · Data · doi:10.3390/data9080092
“Tokens represent smaller units of words, segmented using the WordPiece subword tokenization method outlined in [59].”
MethodHillebrand, L., Pradhan, P., Bauckhage, C., & Sifa, R. (2024) · Lecture notes in computer science · doi:10.1007/978-3-031-70359-1_23
A Cross-linguistic Analysis of the Effects of Character-level Information in Neural Models
Kurosawa, T., & Yanaka, H. (2024) · Journal of Natural Language Processing · doi:10.5715/jnlp.31.1193
Exploiting Multi-Level Data Uncertainty for Japanese-Chinese Neural Machine Translation
Li, Z., Ma, J., & Ren, F. (2024) · IEICE Transactions on Information and Systems · doi:10.1587/transinf.2024edl8059
“Since mBERT works on word pieces rather than tokens (here 𝑤 𝑖 is divided into | 𝑤 | pieces after applying WordPiece [12]), we convert the word piece representations into token-level representations 𝐸 𝑖 and 𝐻 𝑖 by performing a pooling operation on 𝑒 𝑖, 1 , 𝑒 𝑖, 2 , . . . , 𝑒 | 𝑖,𝑤 𝑖 |…”
Samboní-Ortiz, E. A., Garzón-Benítez, P. C., Zúñiga-Hidrobo, L. V., & Rendón, O. M. C. (2024) · IEEE Latin-American Conference on Communications · doi:10.1109/latincom62985.2024.10770684
“Typical tokenizers are BytePairEncoding [27], WordPieceEncoding [28], and Unigram tokenization [29].”
A Cost Minimization Approach to Fix the Vocabulary Size in a Tokenizer for an End-to-End ASR System
Kopparapu, S. K., & Panda, A. (2024) · Lecture notes in computer science · doi:10.1007/978-3-031-78119-3_23
Alonso, O., & Baeza-Yates, R. (2024) · ACM eBooks · doi:10.1145/3674127.3674128
Searching Personal Collections
Bendersky, M., Metzler, D., Najork, M., & Wang, X. (2024) · ACM eBooks · doi:10.1145/3674127.3674142
Query-driven Search Functionality
Li, L. (2024) · ACM eBooks · doi:10.1145/3674127.3674133
Alonso, O., & Baeza-Yates, R. (2024) · ACM eBooks · doi:10.1145/3674127.3702962
Alonso, O., & Baeza-Yates, R. (2024) · ACM eBooks · doi:10.1145/3674127.3674129
Alonso, O., & Baeza-Yates, R. (2024) · ACM eBooks · doi:10.1145/3674127.3702961
Hersh, W., & Roberts, K. E. (2024) · ACM eBooks · doi:10.1145/3674127.3702960
Bast, H., Kalmbach, J., Klumpp, T., & Korzen, C. (2024) · ACM eBooks · doi:10.1145/3674127.3674134 · Cited by 1
Multi-Modal Knowledge Graph Reasoning with Incorporated RulesPreprint
Zhao, J., Chang, Y. Z., Lai, R., Cao, Z., & Zhang, S. (2025) · SSRN Electronic Journal · doi:10.2139/ssrn.5155168
A Comparison of the Feature Extraction and Fine-Tuning Approach to Fake News Detection Using BERT
Chaudhary, V., & Aggarwal, S. (2025) · Communications in computer and information science · doi:10.1007/978-3-031-84394-5_12
A Review of Taxonomy Expansion And its Applications in AI empowering research
Lu, Y., Jiang, K., Zhang, Z., & Zeng, Z. (2024) · International Conference on Intelligent Education and Intelligent Research (IEIR) · doi:10.1109/ieir62538.2024.10960211
Language-specific embeddings of Old English with character-level processingPreprint
Arista, F. J. M., & Rodríguez, D. M. (2025) · Research Square · doi:10.21203/rs.3.rs-6473289/v1
MedSeg: A Statistical Approach to Tokenization Assessment in Medical NLP
Yu, M. (2025) · Journal of Information Systems Engineering & Management · doi:10.52783/jisem.v10i37s.6506
“WordPiece(Schuster & Nakajima, 2012), initially created for machine translation and later widely adopted through BERT(Devlin et al., 2019), incrementally builds its vocabulary by selecting subword units that optimize the language model’s likelihood.”
Prompt-Based Out-of-Distribution Intent Detection
Chow, R., & Lam, A. Y. S. (2025) · IEEE Transactions on Emerging Topics in Computational Intelligence · doi:10.1109/tetci.2024.3372440
“This means that by virtue of the byte-pair encoding used by most language models (BERT uses WordPiece [41] for example), many of the answers, such as “osx”, are not native to the tokenizer’s vocabulary.”
Saha, P., Das, M., & Mukherjee, A. (2025) · Synthesis lectures on human language technologies · doi:10.1007/978-3-031-86595-4_3
Yao, W., & Zhou, W. (2025) · Engineering Reports · doi:10.1002/eng2.70287
“Other studies on multi-scale transformers generate sequences through sub-word segmentation methods such as Byte Pair Encoding (BPE) [10], WordPiece (WP) [11], and SentencePiece (SP) [12].”
Preprocessing and tokenization in prompt engineering
Nayyar, A., Vairamani, A. D., & Kaswan, K. S. (2025) · Elsevier eBooks · doi:10.1016/b978-0-443-33904-2.00010-0
Subword symmetry in natural languages
Pelloni, O., van der Goot, R., Ranacher, P., Vulić, I., & Samardżić, T. (2025) · Royal Society Open Science · doi:10.1098/rsos.250295
“Typically, we distinguish between bottom‑up compression algorithms (byte pair encoding (BPE) [18] and WordPiece [61,62]) and top‑down probabilistic models (Morfessor [63] and the SentencePiece Un‑ igram model [64]).”
Eliminating Non-Overlapping Semantic Misalignment for Cross-Modal Medical Retrieval
Wei, Z., Hou, Z., & Zhou, X. (2025) · IEEE Signal Processing Letters · doi:10.1109/lsp.2025.3602392
“Here, N denotes the number of patches processed by the E V , M represents the number of tokens produced by WordPiece [5] tokenization in the E T , and D l refers to the dimensionality of the local features.”
In Defense of Character-Level Answer Generation Methods for Text-based Visual Question Answering
Nguyen, N. H., Le, P. T., Quan, T., & Nguyen, N. L.-T. (2025) · International Conference on Multimedia Analysis and Pattern Recognition (MAPR) · doi:10.1109/mapr67746.2025.11133907
Automated Multilingual Sentiment Analysis for Psychological Well-Being
Hameed, N. S., Vijayakumar, S., Rajaraman, K., Tamilarasan, P., Panwale, S. B., & Gopinath, N. (2025) · Algorithms for intelligent systems · doi:10.1007/978-981-96-6847-2_18
Adaptive Multimodal Transformer for Personality Trait Assessment in Online Job Interviews
Yi, S., Yamasaki, T., & Yamasaki, T. (2025) · Lecture notes in computer science · doi:10.1007/978-981-95-3459-3_10
Selecting and Combining Large Language Models in Scalable Code Clone Detection
Chochlov, M., Ahmed, G. A., Patten, J. V., Razzaq, A., Han, Y., Guo-xian, L., Gregg, D., & Buckley, J. (2026) · ACM Transactions on Software Engineering and Methodology · doi:10.1145/3838728
“For programming language tasks, the tokenizer processes input sequences, such as source code, and converts the input into a set of unique numerical identifiers that can be understood by an LLM, using the tokenizer’s vocabulary [36, 61, 62].”
SKIP: A Prototype-Based Scalable Knowledge Graph Representation Learning Method
Liu, Y., Liang, K., Xia, J., Liu, M., Yang, X., Liu, X., Zhou, S., & Li, S. Z. (2025) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2025.3625660
“For instance, NodePiece [6], similar to the subword algorithm WordPiece [17], constructs a fixed-size anchor set and then utilizes a designed encoder function to learn entity embeddings.”
Methodology for Creating a Benchmark to Evaluate LLM Performance on Numerals
Karpovich, S. N., Smirnov, A. V., & Teslya, N. (2025) · Informatics and Automation · doi:10.15622/ia.24.6.7
“Современные методы токенизации включают алгоритм Byte Pair Encoding (BPE) [16], который используется в GPT и RoBERTa, алгоритм WordPiece [17], применяемый в моделях BERT, и алгоритм SentencePiece [18], используемый в T5 и ALBERT.”
The Impact of Large Language Models on Healthcare
Kaur, U., Gupta, N., & Kaur, H. (2025) · BENTHAM SCIENCE PUBLISHERS eBooks · doi:10.2174/9798898813512125010012 · Cited by 1
Enhancing Text Representation by Minimizing Bias for Downstream Natural Language Processing Tasks
Zhang, L. (2024) · UNSWorks (University of New South Wales, Sydney, Australia) · doi:10.26190/unsworks/30770
Chung, P., Fong, C. T., Walters, A. M., Yetisgen, M., & O’Reilly-Shah, V. N. (2023) · Figshare · doi:10.6084/m9.figshare.24089258
Chung, P., Fong, C. T., Walters, A. M., Yetisgen, M., & O’Reilly-Shah, V. N. (2023) · Figshare · doi:10.6084/m9.figshare.24089261
Transparent Predictions: Visualizing Mental Health Model Reasoning
Broman, N., & Olsson, R. (2025) · Lund University Publications Student Papers (Lund University)
Puchol, B. (2023) · RiuNet (Universitat Politècnica de València)
Transfer Learning For Spoken Language Processing
Khurana, S. (2023) · DSpace@MIT (Massachusetts Institute of Technology) · Cited by 1
Verkettete Textualität [Concatenative Textuality]
Shoemaker, T. (2024) · eScholarship (California Digital Library)
A Predictive and Interpretable Model for Toxic Content Classification
Xiang, T. (2021) · DigitalGeorgetown (Georgetown University Library)
Gathering signs of mental health concerns through the automated analysis of textual production
Maupomé, D. (2024) · Archipel (Université du Québec à Montréal)
mMERGE: a corpus driven Multiword Expressions discovery algorithm
Youssef, C. B. (2024) · eScholarship (California Digital Library) · Cited by 4
Comparative Analysis of Tokenization Algorithms for Low-Resource Language DzongkhaPreprint
Wangchuk, T., & Gonsalves, T. (2025) · arXiv (Cornell University) · doi:10.48550/arxiv.2509.15255
“WordPiece is very similar to BPE and was first defined in the context of Japanese and Korean Voice Search [16].”
Evaluation of a Hybrid Approach to Legal Entity Recognition
Lopes, F. H., & Garcia, L. P. F. (2025) · doi:10.5753/eniac.2025.14243
“Tokenization, which is crucial for handling complex legal terms (e.g., “desembargadora” → “des”, “##embar”, “##gadora”), was performed us-ing WordPiece for BERT and SentencePiece for XLNet [Schuster and Nakajima 2012, Kudo and Richardson 2018].”
Åström, V., & Norén, A. (2025) · DiVA (Linkoping University)
Skeleton-guided artistic text recognition
Do, T., Tran, T., Le, K., Le, D.-D., & Ngo, T. D. (2025) · International Journal on Document Analysis and Recognition (IJDAR) · doi:10.1007/s10032-025-00565-3
“More advanced models, such as MGP-STR [35], incorporate a hierarchical decoding mechanism with three granularity levels: character, Byte-Pair Encoding (BPE) [36], and WordPiece [37].”
TrafficBM: A Dual-Modality Pre-Training Framework for Network Traffic Classification
Wang, M., Liao, J., Su, J., Wei, Z., Chen, S., Li, Z., & Wang, B. (2025) · IEEE International Performance, Computing, and Communications Conference · doi:10.1109/ipccc66453.2025.11304658 · Cited by 1
“To enable BERT to effectively capture these implicit semantics, we follow ET-BERT [4] and adopt the WordPiece algorithm [24] to construct a vocabulary specifically tailored to network traffic, using bigrams as the minimal token units.”
Old Wine in New Bottles: Using Classical Word Embeddings in Gate-Based Quantum NLP Systems
Ćavar, D., Parukola, K. R., Graves, J. B., & Sparks, S. A. (2026) · Communications in computer and information science · doi:10.1007/978-3-032-13883-5_9
Ziegler, I., Ma, B., Bischl, B., Schubert, B., & Dorigatti, E. (2025) · IEEE International Conference on Bioinformatics and Biomedicine (BIBM) · doi:10.1109/bibm66473.2025.11356154
“This included Byte-Pair Encoding [65, BPE] with vocabularies of 1000 and 50,000, and WordPiece [66, WP] with a 50,000 vocabulary size.”
Zhao, W. X., Zhou, K., Li, J., Tang, T., & Wen, J.-R. (2025) · Artificial intelligence: foundations, theory, and algorithms/Artificial intelligence: Foundations, theory, and algorithms · doi:10.1007/978-981-96-6259-3_4
A Gated Fusion Framework for Multimodal Urdu Named Entity Recognition
Zaidi, E., Fahad, M. S., & Sharma, S. (2025) · International Conference on Pioneering Developments in Computer Science & Digital Technologies (IC2SDT) · doi:10.1109/ic2sdt68218.2025.11383729
“…subsequent steps of the proposed methodology 1) Text and Character Representation: Text tokenization was done through the BERT tokenizer which follows the sub-word strategy of WordPiece introduced by Schuster and Naka-jima [16] which acts as foundation of modern-day Transformer based models.”
Enhancing Kubernetes Cluster Troubleshooting Efficiency With K8sGPT
Puutio, K. (2025) · Tampere University Institutional Repository (Tampere University)
HelBERT: A BERT-Based Pretraining Model for Public Procurement Tasks in Portuguese
Lima, W. E. M., Silva, V. R. D., da Silva, J. C., Rabêlo, R. A. L., & de Paiva, A. C. (2026) · Journal of the Brazilian Computer Society · doi:10.5753/jbcs.2026.5511 · Cited by 1
“To construct the tokenizer, we opt for the WordPiece strategy [Schuster and Nakajima, 2012], which leverages the frequency of subwords in the training corpus.”
Representation learning and deep neural approaches for international trade product classification
Anggoro, A. W. (2025) · ORCA Online Research @Cardiff (Cardiff University)
Martin, S. R. (2025) · Buleria (Universidad de León) · doi:10.18002/10612/28003
Improving Streaming ASR via Differentially Private Fusion of Data from Multiple Sources
Shejwalkar, V., Thakkar, O. D., Chien, S., Rafidi, N., & Narayanan, A. (2025) · IEEE Workshop on Automatic Speech Recognition and Understanding (ASRU) · doi:10.1109/asru65441.2025.11434648
“The output vocabulary has 4096 wordpieces [27].”
Fouille de texte et extraction d'informations dans les données cliniques
Dalloux, C. (2020) · theses.fr (ABES) · doi:10.70675/d09cc9c4z1370z404cz96b2zb4f16b7d15c8 · Cited by 3
Müller, B. (2022) · theses.fr (ABES) · doi:10.70675/6984dc63z4731z4eabzb3fazaf5d012fe143
Few-Shot Intent Classification in User-Generated Short Texts : Application to Conversational Agents
Dopierre, T. (2021) · theses.fr (ABES) · doi:10.70675/ce4875adzcf6ez4960z908dz7dcd0ea70205 · Cited by 1
Word Meaning Representation in Neural Language Models : Lexical Polysemy and Semantic Relationships
Soler, A. G. (2021) · theses.fr (ABES) · doi:10.70675/99a10411zc05ez4135z8f31z13573e0fd4d1
A Data-driven Approach to Natural Language Processing for Contemporary and Historical French
Suárez, P. O. (2022) · theses.fr (ABES) · doi:10.70675/9b4a07fdza641z489fza523zddeee03a6544 · Cited by 1
Passage Retrieval in Standardization Documents
Albarede, L. (2023) · theses.fr (ABES) · doi:10.70675/00952a66z742az4995zb6c4z4e58ac198642
Fake identity & fake activity detection in online social networks based on transfer learning
Zarei, K. (2022) · theses.fr (ABES) · doi:10.70675/ad847383z33f5z4bb7zab0fzafb8c023b56e · Cited by 5
Wang, Y. (2022) · theses.fr (ABES) · doi:10.70675/9bae8e4fz2724z43f3z8be4z7f0367c36fae · Cited by 1
Représentations de phrases interprétables avec autoencodeurs variationnels et attention
Felhi, G. (2023) · theses.fr (ABES) · doi:10.70675/07f34446zf977z4a3bzad50z4145354b3316
Data augmentation and generation for natural language processing
Boulanger, H. (2023) · theses.fr (ABES) · doi:10.70675/d9c78826z1dc1z435dz8620z73a045a9d6a2
Multi-Modal Learning for Video Understanding
Gabeur, V. (2022) · theses.fr (ABES) · doi:10.70675/2b02ff4fzec66z4610z8f97za1abfa8705ff · Cited by 2
Video question answering with limited supervision
Engin, D. (2024) · theses.fr (ABES) · doi:10.70675/c9c7dcf2z4ca3z4e91z9d27zdacd00f76581
TALMed : Traitement Automatique de la Langue Médicale
Bazoge, A. (2024) · theses.fr (ABES) · doi:10.70675/f970ff27z65b9z4988za234zac33e61a0071
Extractiοn d'infοrmatiοn dans des dοcuments histοriques à l'aide de grands mοdèles multimοdaux
Constum, T. (2024) · theses.fr (ABES) · doi:10.70675/3349a122z7f8fz42cezb94dz71729bd1b27e · Cited by 2
Prompt-based Relation Extraction for Pharmacovigilance
Yeh, H.-S. (2024) · theses.fr (ABES) · doi:10.70675/762a3598ze739z4c47za72ez62e5a986fd1f · Cited by 1
Leveraging multi-dimensional context & data augmentation for NER
Luiggi, T. (2025) · theses.fr (ABES) · doi:10.70675/75128aa5z75b0z4644z96b1z04406ee442f3
Stricker, A. (2025) · theses.fr (ABES) · doi:10.70675/5de39489zb287z482bz9c0dzff2cc9103c6f
Bañeras-Roux, T. (2025) · theses.fr (ABES) · doi:10.70675/00266ef3zdc11z494cz821azeb6f6580da5e · Cited by 1
Duperis, Y. (2024) · theses.fr (ABES) · doi:10.70675/eab313daz9534z48cfz9588zd4c6187bc47c
Peuplement semi-automatisé de bases de connaissances à partir de documents non structurés.
Prieur, M. (2025) · theses.fr (ABES) · doi:10.70675/6c995326zb3b9z422dz9e5azbbabf8c75862
Riabi, A. (2025) · theses.fr (ABES) · doi:10.70675/5a649ef5za082z43d8z906azd8051be91d15 · Cited by 4
Classificação de Ideação Suicida em Postagens de Mídias Sociais
Vieira, H. L., & Amancio, D. R. (2025) · doi:10.11606/003296155
Metadata
- Authors
- Schuster, M., & Nakajima, K.
- Affiliations
- Google (United States) (US)
- Venue
- 2012 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)
- Publisher
- IEEE
- Published
- 2012-03
- Pages
- 5149-5152
- ISSN
- 1520-6149 (ISSN-L)
- OpenAlex
- W2121879602
- Cited by
- 862
- References
- 8
- Citations by year
- 2026: 36 · 2025: 66 · 2024: 90 · 2023: 124 · 2022: 137 · 2021: 155 · 2020: 144 · 2019: 59 · 2018: 36 · 2017: 10 · 2016: 3 · 2013: 2
- FWCI
- 0.49
- Type
- conference paper
- Language
- en
- Open access
- closed
- Locations
- IEEE International Conference on Acoustics Speech and Signal Processing (publishedVersion)
- Topics
- Physical Sciences › Computer Science › Artificial Intelligence › Speech Recognition and Synthesis
- Physical Sciences › Computer Science › Artificial Intelligence › Speech and dialogue systems
- Physical Sciences › Computer Science › Artificial Intelligence › Natural Language Processing Techniques
- Keywords
- voice search, Japanese language, Korean language, acoustic modeling
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.