相关论文: SpeechTokenizer: Unified Speech Tokenizer for Spee…

Recently, there has been growing interest in multi-speaker speech recognition, where the utterances of multiple speakers are recognized from their mixture. Promising techniques have been proposed for this task, but earlier works have…

In recent years, large language models have achieved significant success in generative tasks related to speech, audio, music, and other signal domains. A crucial element of these models is the discrete acoustic codecs, which serve as an…

Speech Quality Assessment (SQA) and Continuous Speech Emotion Recognition (CSER) are two key tasks in speech technology, both relying on listener ratings. However, these ratings are inherently biased due to individual listener factors.…

The integration of pre-trained text-based large language models (LLM) with speech input has enabled instruction-following capabilities for diverse speech tasks. This integration requires the use of a speech encoder, a speech adapter, and an…

Discrete audio representation, aka audio tokenization, has seen renewed interest driven by its potential to facilitate the application of text language modeling approaches in audio domain. To this end, various compression and…

We propose an end-to-end speaker-attributed automatic speech recognition model that unifies speaker counting, speech recognition, and speaker identification on monaural overlapped speech. Our model is built on serialized output training…

We propose WHISPER-GPT: A generative large language model (LLM) for speech and music that allows us to work with continuous audio representations and discrete tokens simultaneously as part of a single architecture. There has been a huge…

Speech tokenizers serve as foundational components for speech language models, yet current designs exhibit several limitations, including: 1) dependence on multi-layer residual vector quantization structures or high frame rates, 2) reliance…

We empirically investigate proper pre-training methods to build good visual tokenizers, making Large Language Models (LLMs) powerful Multimodal Large Language Models (MLLMs). In our benchmark, which is curated to evaluate MLLMs visual…

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…

Speech-aware large language models (LLMs) can accept speech inputs, yet their training objectives largely emphasize linguistic content or specific fields such as emotions or the speaker's gender, leaving it unclear whether they encode…

The development of neural audio codecs (NACs) has largely promoted applications of language models (LMs) to speech processing and understanding. However, there lacks the verification on the effectiveness of autoregressive (AR) LMbased…

In this paper, we propose a multi-label classification framework to detect multiple speaking styles in a speech sample. Unlike previous studies that have primarily focused on identifying a single target style, our framework effectively…

In this work, we propose a novel method for modeling numerous speakers, which enables expressing the overall characteristics of speakers in detail like a trained multi-speaker model without additional training on the target speaker's…

In recent years, we have observed a rapid advancement in speech language models (SpeechLLMs), catching up with humans' listening and reasoning abilities. SpeechLLMs have demonstrated impressive spoken dialog question-answering (SQA)…

Speech separation refers to extracting each individual speech source in a given mixed signal. Recent advancements in speech separation and ongoing research in this area, have made these approaches as promising techniques for pre-processing…

Speech large language models (LLMs) have emerged as a prominent research focus in speech processing. We introduce VocalNet-1B and VocalNet-8B, a series of high-performance, low-latency speech LLMs enabled by a scalable and model-agnostic…

To join the advantages of classical and end-to-end approaches for speech recognition, we present a simple, novel and competitive approach for phoneme-based neural transducer modeling. Different alignment label topologies are compared and…

In this paper, we propose StableQuant, a novel adaptive post-training quantization (PTQ) algorithm for widely used speech foundation models (SFMs). While PTQ has been successfully employed for compressing large language models (LLMs) due to…

We introduce Speech-based Intelligence Quotient (SIQ) as a new form of human cognition-inspired evaluation pipeline for voice understanding large language models, LLM Voice, designed to assess their voice understanding ability. Moving…