Tree-structured speaker clustering for fast speaker adaptation

Kosaka, Tetsuo; Sagayama, Shigeki

doi:10.1109/icassp.1994.389309

Cited by 39 publications

(21 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In this experiment, we used a top-down clustering method based on Bhattacharyya distance [17], [23]. Of the constructed tree-structure, the root node is identical to MC-HMMs and the leaf node is the same as single-noise HMMs.…”

Section: Comparison With Other Noise Adaptation Methodsmentioning

confidence: 99%

See 1 more Smart Citation

Speech Recognition under Multiple Noise Environment Based on Multi-Mixture HMM and Weight Optimization by the Aspect Model

Hahm

Ohkawa

Ito

et al. 2010

IEICE Trans. Inf. & Syst.

View full text Add to dashboard Cite

SUMMARYIn this paper, we propose an acoustic model that is robust to multiple noise environments, as well as a method for adapting the acoustic model to an environment to improve the model. The model is called "the multi-mixture model," which is based on a mixture of different HMMs each of which is trained using speech under different noise conditions. Speech recognition experiments showed that the proposed model performs better than the conventional multi-condition model. The method for adaptation is based on the aspect model, which is a "mixture-of-mixture" model. To realize adaptation using extremely small amount of adaptation data (i.e., a few seconds), we train a small number of mixture models, which can be interpreted as models for "clusters" of noise environments. Then, the models are mixed using weights, which are determined according to the adaptation data. The experimental results showed that the adaptation based on the aspect model improved the word accuracy in a heavy noise environment and showed no performance deterioration for all noise conditions, while the conventional methods either did not improve the performance or showed both improvement and degradation of recognition performance according to noise conditions. key words: multi-mixture HMM, noise-independent acoustic model, aspect model, speech recognition in noisy environment

show abstract

Section: Comparison With Other Noise Adaptation Methodsmentioning

confidence: 99%

“…Another noise adaptation approach is based on tree-structured clustering method [21]. In this method, treestructured clustering [17] is performed on various noise and signal-to-noise ratio (SNR) conditions. Then, based on the ML criterion, the HMM that best matches the input speech was selected by tracing the tree from top to bottom.…”

Section: Introductionmentioning

confidence: 99%

Speech Recognition under Multiple Noise Environment Based on Multi-Mixture HMM and Weight Optimization by the Aspect Model

Hahm

Ohkawa

Ito

et al. 2010

IEICE Trans. Inf. & Syst.

View full text Add to dashboard Cite

show abstract

“…Relation (12) implies that the longer the distance between the means m i (m) and m j (m) and the smaller the variances σ 2 i (m) and σ 2 j (m), the higher the value of U ij . The coefficient U ij expresses numerically the law on classification abilities of probability distributions, known from detection theory.…”

Section: Calculation Of Distance D (2)mentioning

confidence: 99%

“…Naito et al (2002) proposed a clustering method based on vocal tract parameters extracted from the signal. Kosaka and Sagayama (1994) proposed the hierarchical clustering (HC) based on probability distances obtained from hidden Markov networks. On the very top of this structure, there is a model encompassing all the speakers, while individual models can be found at the very bottom.…”

Section: Introductionmentioning

confidence: 99%

An Effective Speaker Clustering Method using UBM and Ultra-Short Training Utterances

Hossa¹,

Makowski²

2016

Archives of Acoustics

View full text Add to dashboard Cite

The same speech sounds (phones) produced by different speakers can sometimes exhibit significant differences. Therefore, it is essential to use algorithms compensating these differences in ASR systems. Speaker clustering is an attractive solution to the compensation problem, as it does not require long utterances or high computational effort at the recognition stage. The report proposes a clustering method based solely on adaptation of UBM model weights. This solution has turned out to be effective even when using a very short utterance. The obtained improvement of frame recognition quality measured by means of frame error rate is over 5%.It is noteworthy that this improvement concerns all vowels, even though the clustering discussed in this report was based only on the phoneme a. This indicates a strong correlation between the articulation of different vowels, which is probably related to the size of the vocal tract.

show abstract

“…Popular measures are the Bhattacharyya distance between output probabilities [42] and the probability of generating one speaker's data from another speaker's model after clustering [66]. Yoshizawa et al used sufficient statistics to measure the distance [26], [96].…”

Section: Speaker Clusteringmentioning

confidence: 99%

Acoustic Model Adaptation for Speech Recognition

Sairyo

2010

IEICE Trans. Inf. & Syst.

View full text Add to dashboard Cite

SUMMARYStatistical speech recognition using continuous-density hidden Markov models (CDHMMs) has yielded many practical applications. However, in general, mismatches between the training data and input data significantly degrade recognition accuracy. Various acoustic model adaptation techniques using a few input utterances have been employed to overcome this problem. In this article, we survey these adaptation techniques, including maximum a posteriori (MAP) estimation, maximum likelihood linear regression (MLLR), and eigenvoice. We also present a schematic view called the adaptation pyramid to illustrate how these methods relate to each other. key words: speech recognition, acoustic model adaptation, hidden Markov models

show abstract

Tree-structured speaker clustering for fast speaker adaptation

Cited by 39 publications

References 8 publications

Speech Recognition under Multiple Noise Environment Based on Multi-Mixture HMM and Weight Optimization by the Aspect Model

Speech Recognition under Multiple Noise Environment Based on Multi-Mixture HMM and Weight Optimization by the Aspect Model

An Effective Speaker Clustering Method using UBM and Ultra-Short Training Utterances

Acoustic Model Adaptation for Speech Recognition

Contact Info

Product

Resources

About