158 citations · 895 across the 103 of their papers we have counts for
29 papers · 1 filter
HLT-NUS SUBMISSION FOR 2020 NIST Conversational Telephone Speech SRE
Rohan Kumar Das, Ruijie Tao, Haizhou Li
This work provides a brief description of Human Language Technology (HLT) Laboratory, National University of Singapore (NUS) system submission for 2020 NIST conversational telephon…
Time-Frequency Attention for Monaural Speech Enhancement
Qiquan Zhang, Qi Song, Zhaoheng Ni +2
Most studies on speech enhancement generally don't consider the energy distribution of speech in time-frequency (T-F) representation, which is important for accurate prediction of…
MEmoBERT: Pre-training Model with Prompt-based Learning for Multimodal Emotion Recognition
Jinming Zhao, Ruichen Li, Qin Jin +2
Multimodal emotion recognition study is hindered by the lack of labelled corpora in terms of scale and diversity, due to the high annotation cost and label ambiguity. In this paper…
DeepA: A Deep Neural Analyzer For Speech And Singing Vocoding
Sergey Nikonorov, Berrak Sisman, Mingyang Zhang +1
Conventional vocoders are commonly used as analysis tools to provide interpretable features for downstream tasks such as speech synthesis and voice conversion. They are built under…
StrengthNet: Deep Learning-based Emotion Strength Assessment for Emotional Speech Synthesis
Rui Liu, Berrak Sisman, Haizhou Li
Recently, emotional speech synthesis has achieved remarkable performance. The emotion strength of synthesized speech can be controlled flexibly using a strength descriptor, which i…
Revisiting Self-Training for Few-Shot Learning of Language Model
Yiming Chen, Yan Zhang, Chen Zhang +3
As unlabeled data carry rich task-relevant information, they are proven useful for few-shot learning of language model. The question is how to effectively make use of such data. In…
PL-EESR: Perceptual Loss Based END-TO-END Robust Speaker Representation Extraction
Yi Ma, Kong Aik Lee, Ville Hautamaki +1
Speech enhancement aims to improve the perceptual quality of the speech signal by suppression of the background noise. However, excessive suppression may lead to speech distortion…
Disentanglement of Emotional Style and Speaker Identity for Expressive Voice Conversion
Zongyang Du, Berrak Sisman, Kun Zhou +1
Expressive voice conversion performs identity conversion for emotional speakers by jointly converting speaker identity and emotional style. Due to the hierarchical structure of spe…
Self-supervised Speaker Recognition with Loss-gated Learning
Ruijie Tao, Kong Aik Lee, Rohan Kumar Das +2
In self-supervised learning for speaker recognition, pseudo labels are useful as the supervision signals. It is a known fact that a speaker recognition model doesn't always benefit…
VisualTTS: TTS with Accurate Lip-Speech Synchronization for Automatic Voice Over
Junchen Lu, Berrak Sisman, Rui Liu +2
In this paper, we formulate a novel task to synthesize speech in sync with a silent pre-recorded video, denoted as automatic voice over (AVO). Unlike traditional speech synthesis,…
Exploring Teacher-Student Learning Approach for Multi-lingual Speech-to-Intent Classification
Bidisha Sharma, Maulik Madhavi, Xuehao Zhou +1
End-to-end speech-to-intent classification has shown its advantage in harvesting information from both text and speech. In this paper, we study a technique to develop such an end-t…
USEV: Universal Speaker Extraction with Visual Cue
Zexu Pan, Meng Ge, Haizhou Li
A speaker extraction algorithm seeks to extract the target speaker's speech from a multi-talker speech mixture. The prior studies focus mostly on speaker extraction from a highly o…
Knowledge Distillation from BERT Transformer to Speech Transformer for Intent Classification
Yidi Jiang, Bidisha Sharma, Maulik Madhavi +1
End-to-end intent classification using speech has numerous advantages compared to the conventional pipeline approach using automatic speech recognition (ASR), followed by natural l…
SLoClas: A Database for Joint Sound Localization and Classification
Xinyuan Qian, Bidisha Sharma, Amine El Abridi +1
In this work, we present the development of a new database, namely Sound Localization and Classification (SLoClas) corpus, for studying and analyzing sound localization and classif…
Is Someone Speaking? Exploring Long-term Temporal Features for Audio-visual Active Speaker Detection
Ruijie Tao, Zexu Pan, Rohan Kumar Das +3
Active speaker detection (ASD) seeks to detect who is speaking in a visual scene of one or more speakers. The successful ASD depends on accurate interpretation of short-term and lo…
Serialized Multi-Layer Multi-Head Attention for Neural Speaker Embedding
Hongning Zhu, Kong Aik Lee, Haizhou Li
This paper proposes a serialized multi-layer multi-head attention for neural speaker embedding in text-independent speaker verification. In prior works, frame-level features from o…
Expressive Voice Conversion: A Joint Framework for Speaker Identity and Emotional Style Transfer
Zongyang Du, Berrak Sisman, Kun Zhou +1
Traditional voice conversion(VC) has been focused on speaker identity conversion for speech with a neutral expression. We note that emotional expression plays an essential role in…
Multi-Level Transfer Learning from Near-Field to Far-Field Speaker Verification
Li Zhang, Qing Wang, Kong Aik Lee +2
In far-field speaker verification, the performance of speaker embeddings is susceptible to degradation when there is a mismatch between the conditions of enrollment and test speech…
DynaEval: Unifying Turn and Dialogue Level Evaluation
Chen Zhang, Yiming Chen, Luis Fernando D'Haro +4
A dialogue is essentially a multi-turn interaction among interlocutors. Effective evaluation metrics should reflect the dynamics of such interaction. Existing automatic metrics are…
Selective Listening by Synchronizing Speech with Lips
Zexu Pan, Ruijie Tao, Chenglin Xu +1
A speaker extraction algorithm seeks to extract the speech of a target speaker from a multi-talker speech mixture when given a cue that represents the target speaker, such as a pre…
Multi-target DoA Estimation with an Audio-visual Fusion Mechanism
Xinyuan Qian, Maulik Madhavi, Zexu Pan +2
Most of the prior studies in the spatial \ac{DoA} domain focus on a single modality. However, humans use auditory and visual senses to detect the presence of sound sources. With th…
Emotional Voice Conversion: Theory, Databases and ESD
Kun Zhou, Berrak Sisman, Rui Liu +1
In this paper, we first provide a review of the state-of-the-art emotional voice conversion research, and the existing emotional speech databases. We then motivate the development…
The Multi-speaker Multi-style Voice Cloning Challenge 2021
Qicong Xie, Xiaohai Tian, Guanghou Liu +9
The Multi-speaker Multi-style Voice Cloning Challenge (M2VoC) aims to provide a common sizable dataset as well as a fair testbed for the benchmarking of the popular voice cloning t…
Target Speaker Verification with Selective Auditory Attention for Single and Multi-talker Speech
Chenglin Xu, Wei Rao, Jibin Wu +1
Speaker verification has been studied mostly under the single-talker condition. It is adversely affected in the presence of interference speakers. Inspired by the study on target s…