International Phonetic Alphabet

The International Phonetic Alphabet (IPA) is an alphabetic system of phonetic notation based primarily on the Latin script. It was devised by the International Phonetic Association in the late 19th century as a standardized representation of speech sounds in written form. The IPA is used by lexicographers, foreign language students and teachers, linguists, speech–language pathologists, singers, actors, constructed language creators, and translators. The IPA is designed to represent those qualities of speech that are part of lexical (and, to a limited extent, prosodic) sounds in oral language: phones, intonation and the separation of syllables. To represent additional qualities of speech—such as tooth gnashing, lisping, and sounds made with a cleft lip and cleft palate—an extended set of symbols may be used. Segments are transcribed by one or more IPA symbols of two basic types: letters and diacritics. For example, the sound of the English

Phonetic aware techniques for Speaker Verification

Subhadeep Dey

The goal of this thesis is to improve current state-of-the-art techniques in speaker verification (SV), typically based on âidentity-vectorsâ (i-vectors) and deep neural network (DNN), by exploiting diverse (phonetic) information extracted using various techniques such as automatic speech recognition (ASR). Different speakers span different subspaces within a universal acoustic space, usually modelled by âuniversal background modelâ. The speaker-specific subspace depends on the speakerâs voice characteristics, but also on the verbalised text of a speaker. In current state-of-the-art SV systems, i-vectors are extracted by applying a factor analysis technique to obtain low dimensional speaker-specific representation. Furthermore, DNN output is also employed in a conventional i-vector framework to model phonetic information embedded in the speech signal. This thesis proposes various techniques to exploit phonetic knowledge of speech to further enrich speaker characteristics. More specifically, the techniques proposed in this thesis are applied to various SV tasks, namely, text-independent and text-dependent SV. For text-independent SV task, several ASR systems are developed and applied to compute phonetic posterior probabilities, subsequently exploited to enhance the speaker-specific information included in i-vectors. These approaches are then extended for text-dependent SV task, exploiting temporal information in a principled way, i.e., by using dynamic time warping applied on speaker informative vectors. Finally, as opposed to train DNN with phonetic information, DNN is trained in an end-to-end fashion to directly discriminate speakers. The baseline end-to-end SV approach consists of mapping a variable length speech segment to a fixed dimensional speaker vector by estimating the mean of hidden representations in DNN structure. We improve upon this technique by computing a distance function between two utterances which takes into account common phonetic units. The whole network is optimized by employing a triplet-loss objective function. The proposed approaches are evaluated on commonly used datasets such as NIST SRE 2010 and RSR2015. Significant improvements are observed over the baseline systems on both the text-dependent and text-independent SV tasks by applying phonetic knowledge.

EPFL2018

Phonological Knowledge Guided HMM State Mapping for Cross-Lingual Speaker Adaptation

John David Scott Dines, Hui Liang

Within the HMM state mapping-based cross-lingual speaker adaptation framework, the minimum Kullback-Leibler divergence criterion has been typically employed to measure the similarity of two average voice state distributions from two respective languages for state mapping construction. Considering that this simple criterion doesn't take any language-specific information into account, we propose a data-driven, phonological knowledge guided approach to strengthen the mapping construction -- state distributions from the two languages are clustered according to broad phonetic categories using decision trees and mapping rules are constructed only within each of the clusters. Objective evaluation of our proposed approach demonstrates reduction of mel-cepstral distortion and that mapping rules derived from a single training speaker generalize to other speakers, with subtle improvement being detected during subjective listening tests.

2011

Phonological Knowledge Guided HMM State Mapping for Cross-Lingual Speaker Adaptation

John David Scott Dines, Hui Liang

Idiap2011

Phonetic aware techniques for Speaker Verification

Subhadeep Dey

EPFL2018