Related papers: Improving the transferability of speech separation…

Speech Language Models (SLMs) aim to learn language from raw audio, without textual resources. Despite significant advances, our current models exhibit weak syntax and semantic abilities. However, if the scaling properties of neural…

The sound of our speech is influenced by the places we come from. Great Britain contains a wide variety of distinctive accents which are of interest to linguistics. In particular, the "a" vowel in words like "class" is pronounced…

Speech signals are inherently complex as they encompass both global acoustic characteristics and local semantic information. However, in the task of target speech extraction, certain elements of global and local semantic information in the…

Speech language models (SpeechLMs) accept speech input and produce speech output, allowing for more natural human-computer interaction compared to text-based large language models (LLMs). Traditional approaches for developing SpeechLMs are…

Speech separation is an important problem in speech processing, which targets to separate and generate clean speech from a mixed audio containing speech from different speakers. Empowered by the deep learning technologies over…

Multi-modal based speech separation has exhibited a specific advantage on isolating the target character in multi-talker noisy environments. Unfortunately, most of current separation strategies prefer a straightforward fusion based on…

Speech data collected in real-world scenarios often encounters two issues. First, multiple sources may exist simultaneously, and the number of sources may vary with time. Second, the existence of background noise in recording is inevitable.…

Meta-learning has recently become a research hotspot in speaker verification (SV). We introduce two methods to improve the meta-learning training for SV in this paper. For the first method, a backbone embedding network is first jointly…

Training neural networks for source separation involves presenting a mixture recording at the input of the network and updating network parameters in order to produce an output that resembles the clean source. Consequently, supervised…

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…

Recent studies in zero-shot cross-lingual learning using multilingual models have falsified the previous hypothesis that shared vocabulary and joint pre-training are the keys to cross-lingual generalization. Inspired by this advancement, we…

Personalized speech enhancement (PSE) models achieve promising results compared with unconditional speech enhancement models due to their ability to remove interfering speech in addition to background noise. Unlike unconditional speech…

Learning representative embeddings for different types of speaking styles, such as emotion, age, and gender, is critical for both recognition tasks (e.g., cognitive computing and human-computer interaction) and generative tasks (e.g.,…

The amount of articulatory data available for training deep learning models is much less compared to acoustic speech data. In order to improve articulatory-to-acoustic synthesis performance in these low-resource settings, we propose a…

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…

We propose a new meta learning based framework for low resource speech recognition that improves the previous model agnostic meta learning (MAML) approach. The MAML is a simple yet powerful meta learning approach. However, the MAML presents…

Researches have shown accent classification can be improved by integrating semantic information into pure acoustic approach. In this work, we combine phonetic knowledge, such as vowels, with enhanced acoustic features to build an improved…

Emotion recognition from speech is one of the key steps towards emotional intelligence in advanced human-machine interaction. Identifying emotions in human speech requires learning features that are robust and discriminative across diverse…

Existing studies on self-supervised speech representation learning have focused on developing new training methods and applying pre-trained models for different applications. However, the quality of these models is often measured by the…

Large language models (LLM) have demonstrated the ability to understand human language by leveraging large amount of text data. Automatic speech recognition (ASR) systems are often limited by available transcribed speech data and benefit…