相关论文: Multi-resolution location-based training for multi…

Consonant and vowel reduction are often encountered in speech, which might cause performance degradation in automatic speech recognition (ASR). Our recently proposed learning strategy based on masking, Phone Masking Training (PMT),…

Multilingual automatic speech recognition (ASR) systems mostly benefit low resource languages but suffer degradation in performance across several languages relative to their monolingual counterparts. Limited studies have focused on…

In general, multi-channel source separation has utilized inter-microphone phase differences (IPDs) concatenated with magnitude information in time-frequency domain, or real and imaginary components stacked along the channel axis. However,…

We present a novel approach to end-to-end automatic speech recognition (ASR) that utilizes pre-trained masked language models (LMs) to facilitate the extraction of linguistic information. The proposed models, BERT-CTC and BECTRA, are…

Spoken language recognition (SLR) is the task of automatically identifying the language present in a speech signal. Existing SLR models are either too computationally expensive or too large to run effectively on devices with limited…

While neural methods for text-to-speech (TTS) have shown great advances in modeling multiple speakers, even in zero-shot settings, the amount of data needed for those approaches is generally not feasible for the vast majority of the world's…

Multi-source localization is an important and challenging technique for multi-talker conversation analysis. This paper proposes a novel supervised learning method using deep neural networks to estimate the direction of arrival (DOA) of all…

In speech separation, time-domain approaches have successfully replaced the time-frequency domain with latent sequence feature from a learnable encoder. Conventionally, the feature is separated into speaker-specific ones at the final stage…

Speech generation models based on large language models (LLMs) typically operate on discrete acoustic codes, which differ fundamentally from text tokens due to their multicodebook structure. At each timestep, models must predict N codebook…

Speaker embeddings are promising identity-related features that can enhance the identity assignment performance of a tracking system by leveraging its spatial predictions, i.e, by performing identity reassignment. Common speaker embedding…

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…

Self-supervised learning (SSL) methods which learn representations of data without explicit supervision have gained popularity in speech-processing tasks, particularly for single-talker applications. However, these models often have…

Standard LLM-based speech recognition systems typically process utterances in isolation, limiting their ability to leverage conversational context. In this work, we study whether multimodal context from prior turns improves LLM-based ASR…

Training automatic speech recognition (ASR) systems requires large amounts of data in the target language in order to achieve good performance. Whereas large training corpora are readily available for languages like English, there exists a…

This work introduces sequential neural beamforming, which alternates between neural network based spectral separation and beamforming based spatial separation. Our neural networks for separation use an advanced convolutional architecture…

Large language models have proven themselves highly flexible, able to solve a wide range of generative tasks, such as abstractive summarization and open-ended question answering. In this paper we extend the capabilities of LLMs by directly…

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…

The presence of multiple talkers in the surrounding environment poses a difficult challenge for real-time speech communication systems considering the constraints on network size and complexity. In this paper, we present Personalized…

Speech separation (SS) has advanced significantly with neural network-based methods, showing improved performance on signal-level metrics. However, these methods often struggle to maintain speech intelligibility in the separated signals,…

A three-stage approach is proposed for speaker counting and speech separation in noisy and reverberant environments. In the spatial feature extraction, a spatial coherence matrix (SCM) is computed using whitened relative transfer functions…