Investigating consonant reduction in Mandarin Chinese with improved forced alignment
Abstract
Phonetic reduction has been an important topic in linguistics research. It also presents a great challenge for forced alignment, a technique widely used for automatic phonetic segmentation. In this study, we employed skip-state HMMs to improve forced alignment quality and to make forced alignment applicable to the investigation of phonetic reduction and deletion. With skip-state HMMs, forced alignment accuracy at 10 ms agreement was improved from 73.3% to 75.6% on a corpus of Mandarin Chinese broadcast news speech. Our analysis based on the improved forced alignment of Mandarin broadcast news speech – verified by hand segmentation of a random sample of cases – shows that: 1. The durations of frication and aspiration are additive in the production of plosives and affricates; 2. Plosives are more likely to be deleted than affricates; and 3. Plosives and affricates in higher-frequency words and at word-medial position are more likely to be reduced.
Integrity signals
Registry
Cites
Statistics
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?
Typically developing boys and girls produced even higher UM ratios than adult men and women.
“who were found to produce even higher UM ratios than adult men and women [58–60].”
From Linguistic camouflage in girls with autism spectrum disorder (2017) · cites this paper as [60]
Cites
Davis, S., & Mermelstein, P. (1980) · IEEE Transactions on Acoustics, Speech, and Signal Processing · doi:10.1109/tassp.1980.1163420 · Cited by 5,465 · see citing works
Perceptual linear predictive (PLP) analysis of speech
Heřmanský, H. (1990) · The Journal of the Acoustical Society of America · doi:10.1121/1.399423 · Cited by 2,550 · see citing works
Probabilistic relations between words
Jurafsky, D. S., Bell, A., Gregory, M., & Raymond, W. D. (2001) · Typological studies in language · doi:10.1075/tsl.45.13jur · Cited by 762 · see citing works
Explanation in variable phonology: An exponential model of morphological constraints
Guy, G. R. (1991) · Language Variation and Change · doi:10.1017/s0954394500000429 · Cited by 446 · see citing works
Glottal wave analysis with Pitch Synchronous Iterative Adaptive Inverse Filtering
Alku, P. (1992) · Speech Communication · doi:10.1016/0167-6393(92)90005-r · Cited by 421 · see citing works
Why reduce? Phonological neighborhood density and phonetic reduction in spontaneous speech
Gahl, S., Yao, Y., & Johnson, K. A. (2012) · Journal of Memory and Language · doi:10.1016/j.jml.2011.11.006 · Cited by 345 · see citing works
Massive Reduction In Conversational American English
Johnson, K. L. (2026) · Routledge eBooks · doi:10.4324/9781003763826-9 · Cited by 340 · see citing works
Chen, Y., & Xu, Y. (2006) · Phonetica · doi:10.1159/000091406 · Cited by 160 · see citing works
An introduction to reduced pronunciation variants
Ernestus, M., & Warner, N. L. (2011) · Journal of Phonetics · doi:10.1016/s0095-4470(11)00055-6 · Cited by 130 · see citing works
Speaker-independent phoneme alignment using transition-dependent states
Hosom, J.-P. (2008) · Speech Communication · doi:10.1016/j.specom.2008.11.003 · Cited by 59 · see citing works
Automatic phonetic segmentation using boundary models
Yuan, J., Ryant, N., Liberman, M., Stolcke, A., Mitra, V., & Wang, W. (2013) · Interspeech (USB) · doi:10.21437/interspeech.2013-540 · Cited by 59 · see citing works
Self-citationInvestigating /l/ variation in English through forced alignment
Yuan, J., & Liberman, M. Y. (2009) · Interspeech (USB) · doi:10.21437/interspeech.2009-630 · Cited by 53 · see citing works
Self-citationThe Aligner: Text-to-Speech Alignment Using Markov Models
Wightman, C. W., & Talkin, D. T. (1997) · Springer eBooks · doi:10.1007/978-1-4612-1894-4_25 · Cited by 44 · see citing works
Why Is the Recognition of Spontaneous Speech so Hard?
Furui, S., Nakamura, M., Ichiba, T., et al. (2005) · Lecture notes in computer science · doi:10.1007/11551874_3 · Cited by 29 · see citing works
Automatic detection of “g-dropping” in American English using forced alignment
Yuan, J., & Liberman, M. Y. (2011) · IEEE Workshop on Automatic Speech Recognition and Understanding (ASRU) · doi:10.1109/asru.2011.6163980 · Cited by 29 · see citing works
Self-citationNeural network boundary refining for automatic speech segmentation
Toledano, D. T. (2002) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp.2000.860140 · Cited by 26 · see citing works
MLP-based phone boundary refining for a TTS database
Lee, K.-S. (2006) · IEEE Transactions on Audio Speech and Language Processing · doi:10.1109/tsa.2005.858049 · Cited by 25 · see citing works
Syllable Contractions in a Mandarin Conversational Dialogue Corpus
Tseng, S.-C. (2005) · International Journal of Corpus Linguistics · doi:10.1075/ijcl.10.1.04tse · Cited by 23 · see citing works
Phonetic Boundary Refinement using Support Vector Machine
Lo, H.-Y., & Wang, H. (2007) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp.2007.367224 · Cited by 21 · see citing works
Automatic phonetic segmentation in Mandarin Chinese: Boundary models, glottal features and tone
Yuan, J., Ryant, N., & Liberman, M. Y. (2014) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp.2014.6854058 · Cited by 19 · see citing works
Self-citation
Flagged first, then by citations
Cited by
Sorted by citations
Linguistic camouflage in girls with autism spectrum disorder
Parish-Morris, J., Liberman, M. Y., Cieri, C., Herrington, J. D., Yerys, B. E., Bateman, L., Donaher, J., Ferguson, E., Pandey, J., & Schultz, R. T. (2017) · Molecular Autism · doi:10.1186/s13229-017-0164-6 · Cited by 181 · see citing works
Self-citationAutomatic detection of consonant omission in cleft palate speech
He, L., Wang, X., Zhang, J., Liu, Q., Yin, H., & Lech, M. (2019) · International Journal of Speech Technology · doi:10.1007/s10772-018-09570-w · Cited by 2 · see citing works
- Authors
- Yuan, J., & Liberman, M.
- Affiliations
- University of Pennsylvania (US)
- Venue
- Interspeech 2015
- Publisher
- ISCA
- Published
- 2015-09-06
- Pages
- 2675-2678
- ISSN
- 2308-457X (ISSN-L)
- OpenAlex
- W2400568335
- Cited by
- 13
- References
- 20
- Citations by year
- 2025: 2 · 2024: 1 · 2023: 2 · 2022: 2 · 2021: 1 · 2020: 1 · 2018: 2 · 2017: 1 · 2016: 1
- FWCI
- 0.75
- Type
- conference paper
- Language
- en
- Open access
- closed
- Locations
- Interspeech (USB) (publishedVersion)
- Topics
- Physical Sciences › Computer Science › Artificial Intelligence › Speech Recognition and Synthesis
- Social Sciences › Psychology › Experimental and Cognitive Psychology › Phonetics and Phonology Research
- Physical Sciences › Computer Science › Signal Processing › Speech and Audio Processing
- Keywords
- phonetic reduction, consonant deletion, Mandarin Chinese, forced alignment, phonetic segmentation, broadcast news speech, stop consonants, affricates, frication, aspiration, word frequency, word position
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
