Related papers: LauraTSE: Target Speaker Extraction using Auto-Reg…

Target speech extraction (TSE) extracts the speech of a target speaker in a mixture given auxiliary clues characterizing the speaker, such as an enrollment utterance. TSE addresses thus the challenging problem of simultaneously performing…

We investigate a fully Latent AutoRegressive scheme based on a Gaussian Process (GP) integrated into a Variational Autoencoder (VAE). In this setting, sequential dynamics are transferred from the observation space to a continuous latent…

By representing speaker characteristic as a single fixed-length vector extracted solely from speech, we can train a neural multi-speaker speech synthesis model by conditioning the model on those vectors. This model can also be adapted to…

Large decoder-only language models (LLMs) are the state-of-the-art models on most of today's NLP tasks and benchmarks. Yet, the community is only slowly adopting these models for text embedding tasks, which require rich contextualized…

Target speaker extraction (TSE) aims to isolate individual speaker voices from complex speech environments. The effectiveness of TSE systems is often compromised when the speaker characteristics are similar to each other. Recent research…

We propose self-speculative decoding for speech-aware LLMs by using the CTC encoder as a draft model to accelerate auto-regressive (AR) inference and improve ASR accuracy. Our three-step procedure works as follows: (1) if the frame…

The attention-based encoder-decoder modeling paradigm has achieved promising results on a variety of speech processing tasks like automatic speech recognition (ASR), text-to-speech (TTS) and among others. This paradigm takes advantage of…

Automatic target sound extraction (TSE) is a machine learning approach to mimic the human auditory perception capability of attending to a sound source of interest from a mixture of sources. It often uses a model conditioned on a fixed form…

This paper describes our audio-quality-based multi-strategy approach for the audio-visual target speaker extraction (AVTSE) task in the Multi-modal Information based Speech Processing (MISP) 2023 Challenge. Specifically, our approach adopts…

Recent language model-based text-to-speech (TTS) frameworks demonstrate scalability and in-context learning capabilities. However, they suffer from robustness issues due to the accumulation of errors in speech unit predictions during…

Neural audio codecs (NACs) provide compact latent speech representations in the form of sequences of continuous vectors or discrete tokens. In this work, we investigate how these two types of speech representations compare when used as…

This paper presents a method of sequence-to-sequence (seq2seq) voice conversion using non-parallel training data. In this method, disentangled linguistic and speaker representations are extracted from acoustic features, and voice conversion…

This paper proposes VARA-TTS, a non-autoregressive (non-AR) text-to-speech (TTS) model using a very deep Variational Autoencoder (VDVAE) with Residual Attention mechanism, which refines the textual-to-acoustic alignment layer-wisely.…

Recently, attention-based transformers have become a de facto standard in many deep learning applications including natural language processing, computer vision, signal processing, etc.. In this paper, we propose a transformer-based…

We propose TSELM, a novel target speaker extraction network that leverages discrete tokens and language models. TSELM utilizes multiple discretized layers from WavLM as input tokens and incorporates cross-attention mechanisms to integrate…

Autoregressive decoding in Large Language Models (LLMs) generates one token per step, causing high inference latency. Speculative decoding (SD) mitigates this through a guess-and-verify strategy, but existing training-free variants face…

State-of-the-art Variational Auto-Encoders (VAEs) for learning disentangled latent representations give impressive results in discovering features like pitch, pause duration, and accent in speech data, leading to highly controllable…

We introduces LLaST, a framework for building high-performance Large Language model based Speech-to-text Translation systems. We address the limitations of end-to-end speech translation(E2E ST) models by exploring model architecture design…

Building a universal multilingual automatic speech recognition (ASR) model that performs equitably across languages has long been a challenge due to its inherent difficulties. To address this task we introduce a Language-Agnostic…

Recent zero-shot text-to-speech (TTS) systems face a common dilemma: autoregressive (AR) models suffer from slow generation and lack duration controllability, while non-autoregressive (NAR) models lack temporal modeling and typically…