Model parameter estimation for mixture density polynomial segment models

Fukada, Toshiaki; Paliwal, Kuldip K.; Sagisaka, Yoshinori

doi:10.1006/csla.1998.0047

Cited by 4 publications

(6 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Note that the recognition performance of the BRNN-PSM-based method will be improved by using a more precise PSM whose variant is time variance through a segment [22].…”

Section: Hmm-based Recognition Resultsmentioning

confidence: 99%

See 1 more Smart Citation

Phoneme boundary estimation using bidirectional recurrent neural networks and its applications

1999

View full text Add to dashboard Cite

“…Note that the recognition performance of the BRNN-PSM-based method will be improved by using a more precise PSM whose variant is time variance through a segment [22].…”

Section: Hmm-based Recognition Resultsmentioning

confidence: 99%

“…A segment lattice can be created by fully connecting boundaries existing between main boundaries. This lattice is used for phoneme recognition based on polynomial segment models (PSM) [20,22]. Figure 8 shows a block diagram of the BRNN-PSM-based recognition system.…”

Section: Segment Model-based System 421 Phoneme Segment Lattice Crmentioning

confidence: 99%

Phoneme boundary estimation using bidirectional recurrent neural networks and its applications

1999

View full text Add to dashboard Cite

“…The experimental setup was similar to those reported by Gish and Fukada [13,12] in which classification of 16 vowels sounds, including 13 monothongs and 3 diphthongs was considered. The only difference is that only the 'sx' and 'si' utterances were used for training and evaluation in our experiments with the 'sa' sentences excluded.…”

Section: Methodsmentioning

confidence: 99%

“…In traditional segment models, a single segment is usually used to model each phonetic unit [12]. This has several advantages.…”

Section: Sub-phonetic Modeling Unitsmentioning

confidence: 99%

Consistent Modeling of the Static and Time-Derivative Cepstrums for Speech Recognition Using HSPTM

Lai

Siu

2006

Chinese Spoken Language Processing

View full text Add to dashboard Cite

Abstract. Most speech models represent the static and derivative cepstral features with separate models that can be inconsistent with each other. In our previous work, we proposed the hidden spectral peak trajectory model (HSPTM) in which the static cepstral trajectories are derived from a set of hidden trajectories of the spectral peaks (captured as spectral poles) in the time-frequency domain. In this work, the HSPTM is generalized such that both the static and derivative features are derived from a single set of hidden pole trajectories using the well-known relationship between the spectral poles and cepstral coefficients. As the pole trajectories represent the resonance frequencies across time, they can be interpreted as formant tracks in voiced speech which have been shown to contain important cues for phonemic identification. To preserve the common recognition framework, the likelihood functions are still defined in the cepstral domain with the acoustic models defined by the static and derivative cepstral trajectories. However, these trajectories are no longer separately estimated but jointly derived, and thus are ensured to be consistent with each other. Vowel classification experiments were performed on the TIMIT corpus, using low complexity models (2-mixture). They showed 3% (absolute) classification error reduction compared to the standard HMM of the same complexity.

show abstract

“…E-M re-estimation formulation for mixture PSM was derived in [4] and generalized in [11]. For the E-M training to be efficient, good mixture initializations are needed.…”

Section: Clustering For Mixture Density Modelmentioning

confidence: 99%

Sub-phonetic Polynomial Segment Model for Large Vocabulary Continuous Speech Recognition

Yeung

Siu

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

View full text Add to dashboard Cite

Polynomial Segment Model (PSM) has opened up an alternative research direction for acoustic modeling. In our previous papers [1, 2], we proposed efficient incremental likelihood evaluation and EM training algorithms for PSM, making it possible to train and recognize using PSM alone. In this paper, we shift our focus to make it feasible to use PSM on large vocabulary recognition. First, we used sub-phonetic PSM that represents a phoneme as multiple independent segmental units. Second, we derived and compared different top-down mixture growing approaches that are orders of magnitude more efficient than previously proposed agglomerative clustering techniques. Experimental results show that the top-down clustering performs better than the bottom-up approach. Recognition via N-best re-scoring shows that PSM models outperformed HMM by 7% to 19% on the 5k closed vocabulary Wall Street Journal Nov 92 testset. Our best PSM model achieve 7.15% WER compare with 7.81% use 16 mixture HMM model.

show abstract

Model parameter estimation for mixture density polynomial segment models

Cited by 4 publications

References 9 publications

Phoneme boundary estimation using bidirectional recurrent neural networks and its applications

Phoneme boundary estimation using bidirectional recurrent neural networks and its applications

Consistent Modeling of the Static and Time-Derivative Cepstrums for Speech Recognition Using HSPTM

Sub-phonetic Polynomial Segment Model for Large Vocabulary Continuous Speech Recognition

Contact Info

Product

Resources

About