Related papers: Speaker-Distinguishable CTC: Learning Speaker Dist…

Current sign language translation (SLT) approaches often rely on gloss-based supervision with Connectionist Temporal Classification (CTC), limiting their ability to handle non-monotonic alignments between sign language video and spoken…

In this paper, we propose a novel technique for direct recognition of multiple speech streams given the single channel of mixed speech, without first separating them. Our technique is based on permutation invariant training (PIT) for…

It is challenging to extract semantic meanings directly from audio signals in spoken language understanding (SLU), due to the lack of textual information. Popular end-to-end (E2E) SLU models utilize sequence-to-sequence automatic speech…

The fusion of speech and language in the era of large language models has garnered significant attention. Discrete speech token is often utilized in text-to-speech tasks for speech compression and portability, which is convenient for joint…

Recently, the advance in deep learning has brought a considerable improvement in the end-to-end speech recognition field, simplifying the traditional pipeline while producing promising results. Among the end-to-end models, the connectionist…

The success of retrieval-augmented language models in various natural language processing (NLP) tasks has been constrained in automatic speech recognition (ASR) applications due to challenges in constructing fine-grained audio-text…

This study reports our efforts to improve automatic recognition of suprasegmentals by fine-tuning wav2vec 2.0 with CTC, a method that has been successful in automatic speech recognition. We demonstrate that the method can improve the…

Multi-stage learning is an effective technique to invoke multiple deep-learning modules sequentially. This paper applies multi-stage learning to speech enhancement by using a multi-stage structure, where each stage comprises a…

Monotonic chunkwise attention (MoChA) has been studied for the online streaming automatic speech recognition (ASR) based on a sequence-to-sequence framework. In contrast to connectionist temporal classification (CTC), backward probabilities…

Accurate sequence-to-sequence (seq2seq) alignment is critical for applications like medical speech analysis and language learning tools relying on automatic speech recognition (ASR). State-of-the-art end-to-end (E2E) ASR systems, such as…

In this paper, we propose to improve end-to-end (E2E) spoken language understand (SLU) in an RNN transducer model (RNN-T) by incorporating a joint self-conditioned CTC automatic speech recognition (ASR) objective. Our proposed model is akin…

Query spelling correction is an important function of modern search engines since it effectively helps users express their intentions clearly. With the growing popularity of speech search driven by Automated Speech Recognition (ASR)…

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…

Speaker identification, determining which character said each utterance in literary text, benefits many downstream tasks. Most existing approaches use expert-defined rules or rule-based features to directly approach this task, but these…

In cross-lingual speech synthesis, the speech in various languages can be synthesized for a monoglot speaker. Normally, only the data of monoglot speakers are available for model training, thus the speaker similarity is relatively low…

Spoofing detection systems are typically trained using diverse recordings from multiple speakers, often assuming that the resulting embeddings are independent of speaker identity. However, this assumption remains unverified. In this paper,…

This paper introduces a practical approach for leveraging a real-time deep learning model to alternate between speech enhancement and joint speech enhancement and separation depending on whether the input mixture contains one or two active…

In multi-turn dialogs, natural language understanding models can introduce obvious errors by being blind to contextual information. To incorporate dialog history, we present a neural architecture with Speaker-Sensitive Dual Memory Networks…

This paper presents a description of STC Ltd. systems submitted to the NIST 2021 Speaker Recognition Evaluation for both fixed and open training conditions. These systems consists of a number of diverse subsystems based on using deep neural…

Recent advances in unsupervised representation learning have demonstrated the impact of pretraining on large amounts of read speech. We adapt these techniques for domain adaptation in low-resource -- both in terms of data and compute --…