Global ETD Search
Search theses and dissertations gathered from participating repositories worldwide. Every result links back to the library that holds it. No account is needed.
Results
Showing 1 to 20 of 25 for “"speaker adaptation"”.
-
Learning speech embeddings for speaker adaptation and speech understanding
… to propose modeling approaches in order to learn speaker embeddings for speaker adaptation or to learn semantic speech embeddings. The second goal is to introduce training objectives that achieve fairness for the ASR and SLU problems. In the case of speaker adaptation, we introduce an auxiliary …
-
A Study of the Automatic Speech Recognition Process and Speaker Adaptation
… HMMs. It also discusses various approaches to speaker adaptation such as MLLR and multiscale, and presents experimental results for cross-task speaker adaptation. An analysis of training parameters and data sufficiency for reasonable system performance estimates are also included. It is found …
-
Adaptation of hybrid deep neural network-hidden Markov model speech recognition system using a sub-space approach
… recognition (ASR) system can be enhanced by adaptation of the ASR for a particular speaker or a group of speakers. In ASR, training and testing data often do not follow the same statistics; they are often mismatched, which leads to a gap in performance. The difference between training and …
-
Statistical Recursive Estimation Algorithms for Speaker Adaption
… statistical recursive estimation algorithms for speaker adaptation. In this thesis, a unified framework for recursive maximum likelihood estimation and recursive Bayesian learning is first developed and applied to direct hidden Markov model parameter estimation. Then an online Bayesian learning …
-
Acoustic model selection for recognition of regional accented speech
… that using a small amount of data from a test speaker to choose an accent dependent model using an accent identification system, or building a model using the data from N neighbouring speakers in AID space, will result in superior performance compared to that obtained with unsupervised or …
-
Building personalised speech technology systems with sparse, bad quality or out-of-domain data
… user experience. The possibilities for different speaker identities are practically limitless if short or out-of-domain collections of speech can be used to transfer speaker identity to the synthetic voice. This thesis describes background, methods and results for a group of experiments performed …
-
Automatic Recognition and Assessment of Dysarthric Speech
… autoencoder-based speech enhancement, and speaker adaptation approaches, to improve dysarthric speech recognition and intelligibility assessment. By leveraging both dysarthric and healthy speech corpora, the research enhances automatic speech recognition (ASR) accuracy, enabling more …
-
Disentanglement Learning for Text-Free Voice Conversion
… conversion (VC) aims to change the perceived speaker identity of a speech signal from one to another, while preserving the linguistic content. Recent state-of-the-art VC systems typically are dependent on automatic speech recognition (ASR) models and they have gained great successes. Results …
-
Computational differences between whispered and non-whispered speech
… evaluated. Our approach ef- fectively performs speaker-adaptation for whispered speech acoustic models without needing whispered speech from the target speaker. Results show im- provement over the standard speaker-independent models. Our work opens up additional avenues for research, which are …
-
Speaker Independent Acoustic-to-Articulatory Inversion
… have been successfully implemented for speaker dependent models with parallel acoustic and kinematic training data. However, in many practical applications inversion is needed for new speakers for whom no articulatory data is available. In order to address this problem, this dissertation …
-
Linguistic alignment: The syntactic, prosodic, and segmental phonetic levels
… in their use of words. For example, if one speaker uses the word ‘chips’ while the other says ‘fries’, there is a good chance that one of the two will switch to using the other’s word. Speakers can also adapt to one another in other ways, for example by using a different word order more …
-
Prediction and Enhancement of Speech Intelligibility in Challenging Acoustic Environments
… of bone-conducted speech, with a focus on speaker adaptation.
-
Speaker Normalization for Improved Automatic Speech Recognition for Digital Libraries
… contribution of the work is a new technique for speaker adaptation based on frequency scale modifications. The frequency scale is modified using a minimum mean square error matching of a spectral template for each speaker to a "typical speaker" spectral template. Each spectral template is …
-
Dysarthric Speech Recognition and Offline Handwriting Recognition using Deep Neural Networks
… recent deep learning methods. Also, we apply speaker adaptation methods both at feature level and at parameter level to improve recognition of dysarthric speech.
-
Automatic Speech Recognition Using Deep Neural Networks: New Possibilities
… frequency variations that commonly happen due to speaker and pronunciation differences in speech signals. Moreover, a new CNN structure called limited weight sharing is proposed to better suit special spectral characteristics of speech signals. Our experimental results have shown that the use of a …
-
Spoofing Countermeasures for Voice Biometric System: Feature Extraction, Modelling and Compensation
Automatic speaker verification (ASV) systems have advanced significantly in recent years, but evidence shows that they are susceptible to malicious spoofing attacks such as replay, speech synthesis and voice conversion. The main goal of this thesis is to develop dedicated countermeasures to protect …
-
Deep Neural Network Acoustic Models for ASR
… (MFSC) which help DNN models marginalize out speaker-specific information while focusing on discriminant phonetic features. Various speaker adaptation techniques are also introduced to further improve DNN performance. Another deep acoustic model based on Convolutional Neural Networks (CNN) is …
-
Expanding the Frontier of Speaker-Adaptive TTS: Stronger Generalisation, Less Storage, Wider Languages
Speaker-adaptive text-to-speech (TTS) aims to synthesise speech in a specified target voice by conditioning on one or a few reference utterances. This technology is widely used in personalised voice assistants and audiobooks. Despite recent progress, current systems exhibit limited voice …
-
Maximum-likelihood stochastic transformations for continuous speech recognition
… on the performance degradation due to different speakers and dialects. The second problem is the explicit modeling of the inter-frame correlations in a speaker-independent (SI) system. We attack both of these problems by applying strategies based on the popular family of linear model …
-
Speech Perception in Early Childhood: Contending with Speaker and Accent Variation
… more complex than common intuition may suggest. Speaker-related variation in the realization of words due to changes in speaker gender and accent results in myriad possible realizations of the same word. Although adult listeners can easily accommodate such speaker-specific pronunciations, …
Page 1 of 2