Related papers: Mixture Encoder for Joint Speech Separation and Re…

The goal of multilingual speech technology is to facilitate seamless communication between individuals speaking different languages, creating the experience as though everyone were a multilingual speaker. To create this experience, speech…

We present a decoder-only Conformer for automatic speech recognition (ASR) that processes speech and text in a single stack without external speech encoders or pretrained large language models (LLM). The model uses a modality-aware sparse…

End-to-end transformer-based automatic speech recognition (ASR) systems often capture multiple speech traits in their learned representations that are highly entangled, leading to a lack of interpretability. In this study, we propose the…

End-to-end automatic speech recognition (ASR) systems are increasingly popular due to their relative architectural simplicity and competitive performance. However, even though the average accuracy of these systems may be high, the…

Neural sequence-to-sequence systems deliver state-of-the-art performance for automatic speech recognition (ASR). When using appropriate modeling units, e.g., byte-pair encoded characters, these systems are in principal open vocabulary…

Despite their impressive performance, self-supervised speech models often struggle to generalize to new languages and tend to forget previously acquired knowledge during continual training. To address this, we propose Lamer-SSL, a…

Recent advancements in supervised automatic speech recognition (ASR) have achieved remarkable performance, largely due to the growing availability of large transcribed speech corpora. However, most languages lack sufficient paired speech…

Code-switching (CS) automatic speech recognition (ASR) faces challenges due to the language confusion resulting from accents, auditory similarity, and seamless language switches. Adaptation on the pre-trained multi-lingual model has shown…

This paper presents an audio visual automatic speech recognition (AV-ASR) system using a Transformer-based architecture. We particularly focus on the scene context provided by the visual information, to ground the ASR. We extract…

Code-Switching (CS) multilingual Automatic Speech Recognition (ASR) models can transcribe speech containing two or more alternating languages during a conversation. This paper proposes (1) a new method for creating code-switching ASR…

Employing a monaural speech separation (SS) model as a front-end for automatic speech recognition (ASR) involves balancing two kinds of trade-offs. First, while a larger model improves the SS performance, it also requires a higher…

This work presents our end-to-end (E2E) automatic speech recognition (ASR) model targetting at robust speech recognition, called Integraded speech Recognition with enhanced speech Input for Self-supervised learning representation (IRIS).…

Research on multilingual speech recognition remains attractive yet challenging. Recent studies focus on learning shared structures under the multi-task paradigm, in particular a feature sharing structure. This approach has been found…

Modern automatic speech recognition (ASR) model is required to accurately transcribe diverse speech signals (from different domains, languages, accents, etc) given the specific contextual information in various application scenarios.…

Speech separation has been shown effective for multi-talker speech recognition. Under the ad hoc microphone array setup where the array consists of spatially distributed asynchronous microphones, additional challenges must be overcome as…

Conventional end-to-end automatic speech recognition (ASR) systems rely on paired speech-text data for domain adaptation. Recent LLM-based ASR architectures connect a speech encoder to a large language model via a projection module,…

This paper presents a newly developed, simultaneous neural speech-to-speech translation system and its evaluation. The system consists of three fully-incremental neural processing modules for automatic speech recognition (ASR), machine…

Mixture-of-experts (MoE) architectures have expanded from language modeling to automatic speech recognition (ASR). Traditional MoE methods, such as the Switch Transformer, route experts independently within each layer. Our analysis reveals…

Code-switching deals with alternative languages in communication process. Training end-to-end (E2E) automatic speech recognition (ASR) systems for code-switching is especially challenging as code-switching training data are always…

Speech separation seeks to isolate individual speech signals from a multi-talk speech mixture. Despite much progress, a system well-trained on synthetic data often experiences performance degradation on out-of-domain data, such as…