Segmental HMMs: Modeling Dynamics and Underlying Structure in Speech

Holmes, Wendy

doi:10.1007/978-1-4419-9017-4_7

Cited by 3 publications

(3 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…As was pointed out in Section IV, the analysis of formants separately from hypotheses about what is being said will always be prone to errors (Holmes, 2000). The human labelers knew the identity of the tokens they were labeling, i.e.…”

Section: Discussionmentioning

confidence: 99%

“…Although the quality of phone-dependent HMM2 feature extraction suffers from the fact that HMM2 recognition is error-prone, using such a system (as opposed to, e.g. using just one HMM2 model) is motivated by the assumption that the "... analysis of formants separately from hypotheses about what is being said will always be prone to errors" (Holmes, 2000). In fact, it can be confirmed that, in terms of recognition rates, the features obtained from the phone-dependent HMM2 systems generally perform better than those obtained from a single model.…”

mentioning

confidence: 99%

See 1 more Smart Citation

Evaluation of formant-like features on an automatic vowel classification task

Wet

Weber

Boves

et al. 2004

The Journal of the Acoustical Society of America

View full text Add to dashboard Cite

This study investigates possibilities to find a low-dimensional, formant-related physical representation of speech signals, which is suitable for automatic speech recognition. This aim is motivated by the fact that formants are known to be discriminant features for speech recognition. Combinations of automatically extracted formant-like features and state-of-the-art, noise-robust features have previously been shown to be more robust in adverse conditions than state-of-the-art features alone. However, it is not clear 1 de Wet, JASA how these automatically extracted formant-like features behave in comparison with true formants. The purpose of this paper is to investigate two methods to automatically extract formant-like features, i.e. robust formants and HMM2 features, and to compare these features to hand-labeled formants as well as to mel-frequency cepstral coefficients in terms of their performance on a vowel classification task. The speech data and hand-labeled formants that were used in this study are a subset of the American English vowels database presented in [Hillenbrand et al., J. Acoust. Soc. Am. 97, 3099-3111 (1995)]. Classification performance was measured on the original, clean data as well as in (simulated) adverse conditions. In combination with standard automatic speech recognition methods, the classification performance of the robust formant and HMM2 features compare very well to the performance of the hand-labeled formants.PACS numbers: 43.72.Ne, 43.72.Ar 2 de Wet, JASA I IntroductionHuman speech signals can be described in many different ways (Flanagan, 1972;Rabiner and Schafer, 1978). Some descriptions are directly related to speech production, while others are more suitable for investigating speech perception. Some descriptive frameworks, of which the formant representation is a well-known example, have successfully been applied to both production and perception.Speech production is often modeled as an acoustic source feeding into a linear filter (representing the vocal tract) with little or no interaction between the source and the filter. In terms of this model of acoustic speech production, the phonetically relevant properties of speech signals can be characterized by the resonance frequencies of the filter (to be completed with information on the source, in terms of periodicity and power). It is well known that the frequencies of the first two or three formants are sufficient information for the perceptual identification of vowels (Flanagan, 1972;Minifie et al., 1973). The formant representation is attractive because of its parsimonious character: it allows the representation of speech signals with a very small number of parameters. Not surprisingly, many attempts have been made to exploit the parametric formant representation in speech technology applications such as speech synthesis, speech coding and automatic speech recognition (ASR).A special reason why formants make for an attractive representation of the acoustic characteristics of speech signals is their relation -by virt...

show abstract

Section: Discussionmentioning

confidence: 99%

mentioning

confidence: 99%

Evaluation of formant-like features on an automatic vowel classification task

Wet

Weber

Boves

et al. 2004

The Journal of the Acoustical Society of America

View full text Add to dashboard Cite

show abstract

“…HMMs have been used previously to extract structural information such as formant positions from the speech signal [8,13]. [6] states that the 'analysis of formants separately from hypotheses about what is being said will always prone to errors' and that, for a formant analyzer to be optimal, it should be integrated in a recognition scheme. Following the same line of reasoning, we believe that HMM2 offers a suitable framework for extracting speech structures (such as formant positions), which is supported by encouraging experimental results.…”

Section: Using a Full Hmm2 For Feature Extractionmentioning

confidence: 99%

Speech recognition using advanced HMM2 features

Weber

Bengio

Bourlard

IEEE Workshop on Automatic Speech Recognition and Understanding, 2001. ASRU '01.

View full text Add to dashboard Cite

HMMZ is a particular hidden Markov model where state emission probabilities of the temporal (primary) HMM are modeled through (secondary) state-dependent frequency-based HMMs [IZ]. As shown in [l3], a secondary HMM can also be used to extract robust ASK features. Here, we further investigate this novel approach towards using a full HMMZ as feature extractor, working in the spectral domain, and extracting robust formantlike features for standard ASK system. HMMZ performs a nonlinear, state-dependent frequency warping, and it is shown that the resulting frequency segmentation actually contains particularly discriminant features. To further improve the HMMZ system, we complement the initial spectral energy vectors with frequency information, Finally, adding temporal information to the HMMZ feature vector yields further improvements. These conclusions are experimentally validated on the Numbers95 database, where word error rates of IS%, using only a 4dimensianal feature vector (3 formant-like parameters and one time index) were obtained.

show abstract

A Hidden Trajectory Model with Bi-directional Target-Filtering: Cascaded vs. Integrated Implementation for Phonetic Recognition

Deng

et al.

Proceedings. (ICASSP '05). IEEE International Conference on Acoustics, Speech, and Signal Processing, 2005.

View full text Add to dashboard Cite

Segmental HMMs: Modeling Dynamics and Underlying Structure in Speech

Cited by 3 publications

References 17 publications

Evaluation of formant-like features on an automatic vowel classification task

Evaluation of formant-like features on an automatic vowel classification task

Speech recognition using advanced HMM2 features

A Hidden Trajectory Model with Bi-directional Target-Filtering: Cascaded vs. Integrated Implementation for Phonetic Recognition

Contact Info

Product

Resources

About