Automatic phoneme alignment based on acoustic-phonetic modeling

This paper presents a method for speaker-independent automatic phonetic alignment that is distinguished from standard HMM-based “forced alignment” in three respects: (1) specific acoustic-phonetic features are used, in addition to PLP features, by the phonetic classifier; (2) the units of classification consist of distinctive phonetic features instead of phonemes; and (3) observation probabilities depend not only on the current state, but also on the state transition information. This proposed method is compared with a state-of-the-art baseline forcedalignment system on a number of corpora, including telephone speech, microphone speech, and children’s speech. The new method has agreement of 92.57% within 20 msec on the TIMIT corpus, which is a 26% reduction in error over the baseline method (with 89.95% agreement on TIMIT). Average reduction in error over all corpora is 28%.

• Publication year

  2002

• Venue

  Interspeech

• Publication date

  2002-09-16

• Fields of study

  Linguistics, Computer Science

• Identifiers
  DOI 10.21437/ICSLP.2002-154
• External record

  Open on Semantic Scholar

• Source metadata

  Semantic Scholar

• No claims are published for this paper.

• No concepts are published for this paper.

• Automatic time alignment of phonemes using acoustic-phonetic information

  2000cited by this paper
• Burst detection based on measurements of intensity discrimination

  2000cited by this paper
• High-accuracy automatic segmentation

  1999cited by this paper
• On the use of F0 features in automatic segmentation for speech synthesis

  1998cited by this paper
• Evaluation and integration of neural-network training techniques for continuous digit recognition

  1998cited by this paper
• Universal speech tools: the CSLU toolkit

  1998cited by this paper
• An Introduction to the Psychology of Hearing

  1997cited by this paper
• Syllable-level desynchronisation of phonetic features for speech recognition

  1996cited by this paper
• Labeler agreement in phonetic labeling of continuous speech

  1994cited by this paper
• Automatic segmentation and labeling of speech based on Hidden Markov Models

  1993cited by this paper
• A preliminary statistical evaluation of manual and automatic segmentation discrepancies

  1991cited by this paper

• Analyzing Phonetic and Graphemic Representations in End-to-End Automatic Speech Recognition

  2019cites this paper
• Traces of the Northern Cities Shift:An Empirical Case Study in Amherst, MA

  2016cites this paper
• Expressive speech synthesis : research and system design with hidden Markov models

  2015cites this paper
• Automatic Pronunciation Scoring with Score Combination by Learning to Rank and Class-Normalized DP-Based Quantization

  2015cites this paper
• Modeling coarticulation in continuous speech

  2014influential citation
• Robust neural network-based estimation of articulatory features for Czech

  2014cites this paper
• 英詩における口語(speech)の台頭とその超克 : 詩的言語のイデオロギーとホプキンズ

  2014cites this paper
• Quantification of speech disfluency as a marker of medication-induced cognitive impairment: An application of computerized speech analysis in neuropharmacology

  2013cites this paper
• Automatic transcription and speech recognition of Romanian corpus RO-GRID

  2012cites this paper
• MULTITASK LEARNING TO IMPROVE ARTICULATORY FEATURE ESTIMATION AND PHONEME RECOGNITION

  2011cites this paper
• Automatic speech segmentation for Italian: tools, models, evaluation, and applications

  2011cites this paper
• Mathematical treatment of uncertainty in the speech recognition process

  2010cites this paper
• Robust automatic transcription of English speech corpora

  2010cites this paper
• CASTLE: a computer-assisted stress teaching and learning environment for learners of English as a second language

  2010cites this paper
• Integrating hidden Markov model and PRAAT: a toolbox for robust automatic speech transcription

  2010cites this paper
• EasyAlign : a friendly automatic phonetic alignment tool under Praat

  2010cites this paper
• 文本不特定之自動音素分段演算法 (Text-Independent Automatic Phone Segmentation Algorithm) [In Chinese]

  2010cites this paper
• Using speech transformation to increase speech intelligibility for the hearing- and speaking-impaired

  2009cites this paper
• Robust Detection of Phone Boundaries Using Model Selection Criteria With Few Observations

  2009cites this paper
• Sistema baseado em regras para o refinamento da segmentação automatica de fala

  2008cites this paper
• Phonetic segmentation using multiple speech features

  2008cites this paper
• TRUES: Tone Recognition Using Extended Segments

  2008cites this paper
• Hybridizing conversational and clear speech to determine the degree of contribution of acoustic features to intelligibility.

  2008cites this paper
• Large margin algorithms for discriminative continuous speech recognition (זיהוי דיבור רציף באמצעות אלגוריתמי שוליים רחבים.)

  2007cites this paper
• Large margin algorithms for discriminative continuous speech recognition (זיהוי דיבור רציף באמצעות אלגוריתמי שוליים רחבים.)

  2007cites this paper
• Acoustic-phonetic features for refining the explicit speech segmentation

  2007influential citation
• Monolingual and crosslingual comparison of tandem features derived from articulatory and phone MLPS

  2007cites this paper
• A Large Margin Algorithm for Speech-to-Phoneme and Music-to-Score Alignment

  2007cites this paper
• DERIVED SPOKEN LANGUAGE MARKERS FOR DETECTING MILD COGNITIVE IMPAIRMENT

  2007cites this paper
• Online learning: theory, algorithms and applications (למידה מקוונת.)

  2007cites this paper
• Brazilian Vowels Recognition using a New Hierarchical Decision Structure with Wavelet Packet and SVM

  2007cites this paper
• Segment Boundary Detection via Class Entropy Measurements in Connectionist

  2006cites this paper
• Segment boundary detection via class entropy measurements in connectionist phoneme recognition

  2006influential citation
• Machine Learning Methods for Automatic Speech Recognition and Analysis

  2006cites this paper
• Refining Segmental Boundaries using Support Vector Machine

  2006influential citation
• A New Hierarchical Decision Structure Using Wavelet Packet and SVM for Brazilian Phonemes Recognition

  2006cites this paper
• Phoneme Alignment using Large Margin Techniques

  2005cites this paper
• Phoneme alignment based on discriminative learning

  2005cites this paper
• Comparison of acoustic features of time‐compressed and natural speech

  2004cites this paper
• Diagnostic Assessment of Childhood Apraxia of Speech Using Automatic Speech Recognition (ASR) Methods.

  2004cites this paper