5 citations · 10 across the 19 of their papers we have counts for
20 papers
CAFE: Confining Feature Distillation to Language-Routed Adapters for Compact Multilingual Automatic Speech Recognition
Tianchi Liu, Nicholas Moratelli, Khurram Azeem Hashmi +5
Feature distillation is usually expected to add to logit distillation. We find that this expectation does not hold for two common feature losses in compact multilingual automatic s…
PhiNet: Speaker Verification with Phonetic Interpretability
Yi Ma, Shuai Wang, Tianchi Liu +1
Despite remarkable progress, automatic speaker verification (ASV) systems typically lack the transparency required for high-accountability applications. Motivated by how human expe…
Benchmarking Contextual and Paralinguistic Reasoning in Speech-LLMs: A Case Study with In-the-Wild Data
Qiongqiong Wang, Hardik Bhupendra Sailor, Tianchi Liu +7
Recent speech-LLMs have shown impressive performance in tasks like transcription and translation, yet they remain limited in understanding the paralinguistic aspects of speech cruc…
Interpolating Speaker Identities in Embedding Space for Data Expansion
Tianchi Liu, Ruijie Tao, Qiongqiong Wang +5
The success of deep learning-based speaker verification systems is largely attributed to access to large-scale and diverse speaker identity data. However, collecting data from more…
Incorporating Contextual Paralinguistic Understanding in Large Speech-Language Models
Qiongqiong Wang, Hardik B. Sailor, Jeremy H. M. Wong +6
Current large speech language models (Speech-LLMs) often exhibit limitations in empathetic reasoning, primarily due to the absence of training datasets that integrate both contextu…
Contextual Paralinguistic Data Creation for Multi-Modal Speech-LLM: Data Condensation and Spoken QA Generation
Qiongqiong Wang, Hardik B. Sailor, Tianchi Liu +1
Current speech-LLMs exhibit limited capability in contextual reasoning alongside paralinguistic understanding, primarily due to the lack of Question-Answer (QA) datasets that cover…
Nes2Net: A Lightweight Nested Architecture for Foundation Model Driven Speech Anti-spoofing
Tianchi Liu, Duc-Tuan Truong, Rohan Kumar Das +2
Speech foundation models have significantly advanced various speech-related tasks by providing exceptional representation capabilities. However, their high-dimensional output featu…
ExPO: Explainable Phonetic Trait-Oriented Network for Speaker Verification
Yi Ma, Shuai Wang, Tianchi Liu +1
In speaker verification, we use computational method to verify if an utterance matches the identity of an enrolled speaker. This task is similar to the manual task of forensic voic…
MERaLiON-SpeechEncoder: Towards a Speech Foundation Model for Singapore and Beyond
Muhammad Huzaifah, Geyu Lin, Tianchi Liu +8
This technical report describes the MERaLiON-SpeechEncoder, a foundation model designed to support a wide range of downstream speech applications. Developed as part of Singapore's…
Towards Quantifying and Reducing Language Mismatch Effects in Cross-Lingual Speech Anti-Spoofing
Tianchi Liu, Ivan Kukanov, Zihan Pan +3
The effects of language mismatch impact speech anti-spoofing systems, while investigations and quantification of these effects remain limited. Existing anti-spoofing datasets are m…
Speech Foundation Model Ensembles for the Controlled Singing Voice Deepfake Detection (CtrSVDD) Challenge 2024
Anmol Guragain, Tianchi Liu, Zihan Pan +2
This work details our approach to achieving a leading system with a 1.79% pooled equal error rate (EER) on the evaluation set of the Controlled Singing Voice Deepfake Detection (Ct…
Attentive Merging of Hidden Embeddings from Pre-trained Speech Model for Anti-spoofing Detection
Zihan Pan, Tianchi Liu, Hardik B. Sailor +1
Self-supervised learning (SSL) speech representation models, trained on large speech corpora, have demonstrated effectiveness in extracting hierarchical speech embeddings through m…
How Do Neural Spoofing Countermeasures Detect Partially Spoofed Audio?
Tianchi Liu, Lin Zhang, Rohan Kumar Das +3
Partially manipulating a sentence can greatly change its meaning. Recent work shows that countermeasures (CMs) trained on partially spoofed audio can effectively detect such spoofi…
Voice Conversion Augmentation for Speaker Recognition on Defective Datasets
Ruijie Tao, Zhan Shi, Yidi Jiang +2
Modern speaker recognition system relies on abundant and balanced datasets for classification training. However, diverse defective datasets, such as partially-labelled, small-scale…
Golden Gemini is All You Need: Finding the Sweet Spots for Speaker Verification
Tianchi Liu, Kong Aik Lee, Qiongqiong Wang +1
Previous studies demonstrate the impressive performance of residual neural networks (ResNet) in speaker verification. The ResNet models treat the time and frequency dimensions equa…
Disentangling Voice and Content with Self-Supervision for Speaker Recognition
Tianchi Liu, Kong Aik Lee, Qiongqiong Wang +1
For speaker recognition, it is difficult to extract an accurate speaker representation from speech because of its mixture of speaker traits and content. This paper proposes a disen…
Incorporating Uncertainty from Speaker Embedding Estimation to Speaker Verification
Qiongqiong Wang, Kong Aik Lee, Tianchi Liu
Speech utterances recorded under differing conditions exhibit varying degrees of confidence in their embedding estimates, i.e., uncertainty, even if they are extracted using the sa…
Scoring of Large-Margin Embeddings for Speaker Verification: Cosine or PLDA?
Qiongqiong Wang, Kong Aik Lee, Tianchi Liu
The emergence of large-margin softmax cross-entropy losses in training deep speaker embedding neural networks has triggered a gradual shift from parametric back-ends to a simpler c…
MFA: TDNN with Multi-scale Frequency-channel Attention for Text-independent Speaker Verification with Short Utterances
Tianchi Liu, Rohan Kumar Das, Kong Aik Lee +1
The time delay neural network (TDNN) represents one of the state-of-the-art of neural solutions to text-independent speaker verification. However, they require a large number of fi…
Speaker-Utterance Dual Attention for Speaker and Utterance Verification
Tianchi Liu, Rohan Kumar Das, Maulik Madhavi +2
In this paper, we study a novel technique that exploits the interaction between speaker traits and linguistic content to improve both speaker verification and utterance verificatio…