Related papers: Acquiring Pronunciation Knowledge from Transcribed…

Furui first demonstrated that the identity of both consonant and vowel can be perceived from the C-V transition; later, Stevens proposed that acoustic landmarks are the primary cues for speech perception, and that steady-state regions are…

Despite the close relationship between speech perception and production, research in automatic speech recognition (ASR) and text-to-speech synthesis (TTS) has progressed more or less independently without exerting much mutual influence on…

Building a good speech recognition system usually requires large amounts of transcribed data, which is expensive to collect. To tackle this problem, many unsupervised pre-training methods have been proposed. Among these methods, Masked…

Speech-to-text translation (ST), which translates source language speech into target language text, has attracted intensive attention in recent years. Compared to the traditional pipeline system, the end-to-end ST model has potential…

In the traditional cascading architecture for spoken language understanding (SLU), it has been observed that automatic speech recognition errors could be detrimental to the performance of natural language understanding. End-to-end (E2E) SLU…

This paper presents a transfer learning method in speech emotion recognition based on a Time-Delay Neural Network (TDNN) architecture. A major challenge in the current speech-based emotion detection research is data scarcity. The proposed…

Self-supervised learning (SSL) based speech pre-training has attracted much attention for its capability of extracting rich representations learned from massive unlabeled data. On the other hand, the use of weakly-supervised data is less…

Self-supervised learning (SSL) techniques have achieved remarkable results in various speech processing tasks. Nonetheless, a significant challenge remains in reducing the reliance on vast amounts of speech data for pre-training. This paper…

Spoken language understanding is typically based on pipeline architectures including speech recognition and natural language understanding steps. These components are optimized independently to allow usage of available data, but the overall…

Recently, data-driven based Automatic Speech Recognition (ASR) systems have achieved state-of-the-art results. And transfer learning is often used when those existing systems are adapted to the target domain, e.g., fine-tuning, retraining.…

Automatic speech recognition (ASR) of single channel far-field recordings with an unknown number of speakers is traditionally tackled by cascaded modules. Recent research shows that end-to-end (E2E) multi-speaker ASR models can achieve…

Deep learning models are becoming predominant in many fields of machine learning. Text-to-Speech (TTS), the process of synthesizing artificial speech from text, is no exception. To this end, a deep neural network is usually trained using a…

The present study tackles the problem of automatically discovering spoken keywords from untranscribed audio archives without requiring word-by-word speech transcription by automatic speech recognition (ASR) technology. The problem is of…

We propose a multitask training method for attention-based end-to-end speech recognition models. We regularize the decoder in a listen, attend, and spell model by multitask training it on both audio-text and text-only data. Trained on the…

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…

In this paper, we propose an incremental learning method for end-to-end Automatic Speech Recognition (ASR) which enables an ASR system to perform well on new tasks while maintaining the performance on its originally learned ones. To…

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…

This paper investigates different pretraining approaches to spoken language identification. The paper is based on our submission to the Oriental Language Recognition 2021 Challenge. We participated in two tracks of the challenge:…

End-to-end Speech-to-text Translation (E2E-ST), which directly translates source language speech to target language text, is widely useful in practice, but traditional cascaded approaches (ASR+MT) often suffer from error propagation in the…

Audio-LLM introduces audio modality into a large language model (LLM) to enable a powerful LLM to recognize, understand, and generate audio. However, during speech recognition in noisy environments, we observed the presence of illusions and…