相关论文: Adapting Speech Separation to Real-World Meetings …

In this paper, we propose MixSpeech, a simple yet effective data augmentation method based on mixup for automatic speech recognition (ASR). MixSpeech trains an ASR model by taking a weighted combination of two different speech features…

In recent years, deep learning based source separation has achieved impressive results. Most studies, however, still evaluate separation models on synthetic datasets, while the performance of state-of-the-art techniques on in-the-wild…

Distant-microphone meeting transcription is a challenging task. State-of-the-art end-to-end speaker-attributed automatic speech recognition (SA-ASR) architectures lack a multichannel noise and reverberation reduction front-end, which limits…

Automatic Speech Recognition (ASR) has advanced with Speech Foundation Models (SFMs), yet performance degrades on dysarthric speech due to variability and limited data. This study as part of the submission to the Speech Accessibility…

Target speech separation refers to extracting a target speaker's voice from an overlapped audio of simultaneous talkers. Previously the use of visual modality for target speech separation has demonstrated great potentials. This work…

This paper examines the implications of using the Scale-Invariant Signal-to-Distortion Ratio (SI-SDR) as both evaluation and training objective in supervised speech separation, when the training references contain noise, as is the case with…

Since the first speech recognition systems were built more than 30 years ago, improvement in voice technology has enabled applications such as smart assistants and automated customer support. However, conversation intelligence of the future…

Many real-life applications of automatic speech recognition (ASR) require processing of overlapped speech. A common method involves first separating the speech into overlap-free streams on which ASR is performed. Recently, TF-GridNet has…

This paper presents a novel deep learning architecture for acoustic model in the context of Automatic Speech Recognition (ASR), termed as MixNet. Besides the conventional layers, such as fully connected layers in DNN-HMM and memory cells in…

Many recent source separation systems are designed to separate a fixed number of sources out of a mixture. In the cases where the source activation patterns are unknown, such systems have to either adjust the number of outputs or to…

Reverberation as supervision (RAS) is a framework that allows for training monaural speech separation models from multi-channel mixtures in an unsupervised manner. In RAS, models are trained so that sources predicted from a mixture at an…

In this paper we propose to use utterance-level Permutation Invariant Training (uPIT) for speaker independent multi-talker speech separation and denoising, simultaneously. Specifically, we train deep bi-directional Long Short-Term Memory…

Single channel speech separation has experienced great progress in the last few years. However, training neural speech separation for a large number of speakers (e.g., more than 10 speakers) is out of reach for the current methods, which…

Binaural speech separation in real-world scenarios often involves moving speakers. Most current speech separation methods use utterance-level permutation invariant training (u-PIT) for training. In inference time, however, the order of…

We propose multi-microphone complex spectral mapping, a simple way of applying deep learning for time-varying non-linear beamforming, for speaker separation in reverberant conditions. We aim at both speaker separation and dereverberation.…

In this paper, we present our overall efforts to improve the performance of a code-switching speech recognition system using semi-supervised training methods from lexicon learning to acoustic modeling, on the South East Asian…

Supervised speech enhancement relies on parallel databases of degraded speech signals and their clean reference signals during training. This setting prohibits the use of real-world degraded speech data that may better represent the…

Transformers, which were originally developed for natural language processing, have recently generated significant interest in the computer vision and audio communities due to their flexibility in learning long-range relationships.…

Permutation invariant training (PIT) is a widely used training criterion for neural network-based source separation, used for both utterance-level separation with utterance-level PIT (uPIT) and separation of long recordings with the…

State-of-the-art large-scale universal speech models (USMs) show a decent automatic speech recognition (ASR) performance across multiple domains and languages. However, it remains a challenge for these models to recognize overlapped speech,…