Clustering of triphones using phoneme similarity estimation for the definition of a multilingual set of triphones

Imperl, Bojan; Kačič, Zdravko; Horvat, Bogomir; Žgank, Andrej

doi:10.1016/s0167-6393(02)00048-1

Cited by 11 publications

(8 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…TIMIT has been chosen because it includes accurate time-aligned phonetic transcriptions, meaning that both phonetic labels and their start/end times are known. As our desired clusters we use triphones, which are phones in specific left and right contexts [27]. We consider triphones that occur at least 20 times and at most 25 times in the corpus.…”

Section: Datamentioning

confidence: 99%

Feature trajectory dynamic time warping for clustering of speech segments

Lerato

Niesler

2019

J AUDIO SPEECH MUSIC PROC.

View full text Add to dashboard Cite

Dynamic time warping (DTW) can be used to compute the similarity between two sequences of generally differing length. We propose a modification to DTW that performs individual and independent pairwise alignment of feature trajectories. The modified technique, termed feature trajectory dynamic time warping (FTDTW), is applied as a similarity measure in the agglomerative hierarchical clustering of speech segments. Experiments using MFCC and PLP parametrisations extracted from TIMIT and from the Spoken Arabic Digit Dataset (SADD) show consistent and statistically significant improvements in the quality of the resulting clusters in terms of F-measure and normalised mutual information (NMI).

show abstract

Section: Datamentioning

confidence: 99%

Feature trajectory dynamic time warping for clustering of speech segments

Lerato

Niesler

2019

J AUDIO SPEECH MUSIC PROC.

View full text Add to dashboard Cite

show abstract

“…Several similarity measure proposals can be found in literature [4,16,25], but as referred in [26], they do not fulfil the properties of a proper metric. In the present proposal, d 1 has the three metric properties: it is positive, symmetric and satisfies the triangle inequality.…”

Section: Similarity Measurementioning

confidence: 99%

“…The key point of all clustering algorithms is the choice of a proximity or distance measure. This measure can be obtained from acoustic models, e.g., [3,15], or even rely on the confusion matrix, e.g., [4,16]. Model-driven methods and confusiondriven a methods are then the two major categories of datadriven phone clustering algorithms.…”

Section: Introductionmentioning

confidence: 99%

Broad phonetic class definition driven by phone confusions

Lopes

Perdigão

2012

EURASIP J. Adv. Signal Process.

View full text Add to dashboard Cite

Intermediate representations between the speech signal and phones may be used to improve discrimination among phones that are often confused. These representations are usually found according to broad phonetic classes, which are defined by a phonetician. This article proposes an alternative data-driven method to generate these classes. Phone confusion information from the analysis of the output of a phone recognition system is used to find clusters at high risk of mutual confusion. A metric is defined to compute the distance between phones. The results, using TIMIT data, show that the proposed confusion-driven phone clustering method is an attractive alternative to the approaches based on human knowledge. A hierarchical classification structure to improve phone recognition is also proposed using a discriminative weight training method. Experiments show improvements in phone recognition on the TIMIT database compared to a baseline system.

show abstract

“…In data-driven methods, similarity between phonetic units across languages is commonly estimated by evaluating the distance of their language-dependent acoustic models (i.e. HMMs) using agglomerative (Kö hler, 2001;Salvi, 2003;Imperl et al, 2003), decision tree based (Schultz and Waibel, 2001), or a combination of decision tree and agglomerative (Mariñ o et al, 2000) clustering algorithms. Other data-driven approaches find the similarity between phones by means of a confusion matrix (Byrne et al, 2000).…”

Section: Introductionmentioning

confidence: 99%

“…Other data-driven approaches find the similarity between phones by means of a confusion matrix (Byrne et al, 2000). Measuring similarity between language-context-dependent phonetic units, such as demiphones (Mariñ o et al, 2000), triphones (Imperl et al, 2003) or pentaphones (Schultz and Waibel, 2001) provide better recognition results than measuring similarity between language-context-independent units. In addition, (Imperl et al, 2003) conclude that although an agglomerative clustering algorithm yields a limited number of clusters, the decision tree method gives better recognition results and solves modeling units that are not seen in the training data.…”

Section: Introductionmentioning

confidence: 99%

Multidialectal Spanish acoustic modeling for speech recognition

Caballero¹,

Moreno²,

Nogueiras³

2009

Speech Communication

View full text Add to dashboard Cite

During the last years, language resources for speech recognition have been collected for many languages and specifically, for global languages. One of the characteristics of global languages is their wide geographical dispersion, and consequently, their wide phonetic, lexical, and semantic dialectal variability. Even if the collected data is huge, it is difficult to represent dialectal variants accurately.This paper deals with multidialectal acoustic modeling for Spanish. The goal is to create a set of multidialectal acoustic models that represents the sounds of the Spanish language as spoken in Latin America and Spain. A comparative study of different methods for combining data between dialects is presented. The developed approaches are based on decision tree clustering algorithms. They differ on whether a multidialectal phone set is defined, and in the decision tree structure applied.Besides, a common overall phonetic transcription for all dialects is proposed. This transcription can be used in combination with all the proposed acoustic modeling approaches. Overall transcription combined with approaches based on defining a multidialectal phone set leads to a full dialect-independent recognizer, capable to recognize any dialect even with a total absence of training data from such dialect.Multidialectal systems are evaluated over data collected in five different countries: Spain, Colombia, Venezuela, Argentina and Mexico. The best results given by multidialectal systems show a relative improvement of 13% over the results obtained with monodialectal systems. Experiments with dialect-independent systems have been conducted to recognize speech from Chile, a dialect not seen in the training process. The recognition results obtained for this dialect are similar to the ones obtained for other dialects.

show abstract

Clustering of triphones using phoneme similarity estimation for the definition of a multilingual set of triphones

Cited by 11 publications

References 13 publications

Feature trajectory dynamic time warping for clustering of speech segments

Feature trajectory dynamic time warping for clustering of speech segments

Broad phonetic class definition driven by phone confusions

Multidialectal Spanish acoustic modeling for speech recognition

Contact Info

Product

Resources

About