Related papers: Training Strategies for Modality Dropout Resilient…

Target Speech Extraction (TSE) aims to isolate a target speaker's voice from a mixture of multiple speakers by leveraging speaker-specific cues, typically provided as auxiliary audio (a.k.a. cue audio). Although recent advancements in TSE…

We propose a Beamformer-guided Target Speaker Extraction (BG-TSE) method to extract a target speaker's voice from a multi-channel recording informed by the direction of arrival of the target. The proposed method employs a front-end…

Speech separation seeks to isolate individual speech signals from a multi-talk speech mixture. Despite much progress, a system well-trained on synthetic data often experiences performance degradation on out-of-domain data, such as…

State-of-the-art target speaker extraction (TSE) systems are typically designed to generalize to any given mixing environment, necessitating a model with a large enough capacity as a generalist. Personalized speech enhancement could be a…

Reliable channel estimation (CE) is fundamental for robust communication in dynamic wireless environments, where models must generalize across varying conditions such as signal-to-noise ratios (SNRs), the number of resource blocks (RBs),…

Speech emotion recognition (SER) plays a critical role in building emotion-aware speech systems, but its performance degrades significantly under noisy conditions. Although speech enhancement (SE) can improve robustness, it often introduces…

Speaker extraction algorithm relies on the speech sample from the target speaker as the reference point to focus its attention. Such a reference speech is typically pre-recorded. On the other hand, the temporal synchronization between…

We present MoST (Mixture of Speech and Text), a novel multimodal large language model that seamlessly integrates speech and text processing through our proposed Modality-Aware Mixture of Experts (MAMoE) architecture. While current…

This research combines Knowledge Distillation (KD) and Mixture of Experts (MoE) to develop modular, efficient multilingual language models. Key objectives include evaluating adaptive versus fixed alpha methods in KD and comparing modular…

End-to-end speech-to-text translation (E2E-ST) is becoming increasingly popular due to the potential of its less error propagation, lower latency, and fewer parameters. Given the triplet training corpus $\langle speech, transcription,…

Multivariate time series(MTS) is a universal data type related to many practical applications. However, MTS suffers from missing data problems, which leads to degradation or even collapse of the downstream tasks, such as prediction and…

Multilingual neural machine translation (MNMT) learns to translate multiple language pairs with a single model, potentially improving both the accuracy and the memory-efficiency of deployed models. However, the heavy data imbalance between…

This work presents a lifelong learning approach to train a multilingual Text-To-Speech (TTS) system, where each language was seen as an individual task and was learned sequentially and continually. It does not require pooled data from all…

Targeted syntactic evaluation of subject-verb number agreement in English (TSE) evaluates language models' syntactic knowledge using hand-crafted minimal pairs of sentences that differ only in the main verb's conjugation. The method…

We present MParrotTTS, a unified multilingual, multi-speaker text-to-speech (TTS) synthesis model that can produce high-quality speech. Benefiting from a modularized training paradigm exploiting self-supervised speech representations,…

Target speech extraction (TSE) typically relies on pre-recorded high-quality enrollment speech, which disrupts user experience and limits feasibility in spontaneous interaction. In this paper, we propose Enroll-on-Wakeup (EoW), a novel…

End-to-end (E2E) spoken language understanding (SLU) systems can infer the semantics of a spoken utterance directly from an audio signal. However, training an E2E system remains a challenge, largely due to the scarcity of paired…

Predicting the altered acoustic frames is an effective way of self-supervised learning for speech representation. However, it is challenging to prevent the pretrained model from overfitting. In this paper, we proposed to introduce two…

Sparsely activated transformers, such as Mixture of Experts (MoE), have received great interest due to their outrageous scaling capability which enables dramatical increases in model size without significant increases in computational cost.…

Multi-speaker TTS has to learn both linguistic embedding and text embedding to generate speech of desired linguistic content in desired voice. However, it is unclear which characteristic of speech results from speaker and which part from…