Related papers: Transducer-based language embedding for spoken lan…

Spoken language diarization (LD) and related tasks are mostly explored using the phonotactic approach. Phonotactic approaches mostly use explicit way of language modeling, hence requiring intermediate phoneme modeling and transcribed data.…

One of the methods for language Identification (LID) involves deriving speech representation from pre-trained models using self-supervised learning, followed by fine-tuning the model for the LID task. State-of-the-art approaches for LID use…

Target-speaker speech recognition aims to recognize target-speaker speech from noisy environments with background noise and interfering speakers. This work presents a joint framework that combines time-domain target-speaker speech…

Spoken language Identification (LID) systems are needed to identify the language(s) present in a given audio sample, and typically could be the first step in many speech processing related tasks such as automatic speech recognition (ASR).…

We propose and evaluate transformer-based acoustic models (AMs) for hybrid speech recognition. Several modeling choices are discussed in this work, including various positional embedding methods and an iterated loss to enable training deep…

End-to-end automatic speech recognition (ASR) models with a single neural network have recently demonstrated state-of-the-art results compared to conventional hybrid speech recognizers. Specifically, recurrent neural network transducer…

This paper introduces a highly efficient greedy decoding algorithm for Transducer-based speech recognition models. We redesign the standard nested-loop design for RNN-T decoding, swapping loops over frames and labels: the outer loop…

Attention-based contextual biasing approaches have shown significant improvements in the recognition of generic and/or personal rare-words in End-to-End Automatic Speech Recognition (E2E ASR) systems like neural transducers. These…

Language Identification (LID) is an important component of many multilingual natural language processing pipelines, where it facilitates corpus curation, training data analysis, and cross-lingual evaluation of large language models. Despite…

In recent years, end-to-end (E2E) based automatic speech recognition (ASR) systems have achieved great success due to their simplicity and promising performance. Neural Transducer based models are increasingly popular in streaming E2E based…

Phonotactic constraints can be employed to distinguish languages by representing a speech utterance as a multinomial distribution or phone events. In the present study, we propose a new learning mechanism based on subspace-based…

We introduce an approach to identifying speaker names in dialogue transcripts, a crucial task for enhancing content accessibility and searchability in digital media archives. Despite the advancements in speech recognition, the task of…

This paper proposes a novel Recurrent Neural Network (RNN) language model that takes advantage of character information. We focus on character n-grams based on research in the field of word embedding construction (Wieting et al. 2016). Our…

We present a comprehensive study on building and adapting RNN transducer (RNN-T) models for spoken language understanding(SLU). These end-to-end (E2E) models are constructed in three practical settings: a case where verbatim transcripts are…

Retrieval is a widely adopted approach for improving language models leveraging external information. As the field moves towards multi-modal large language models, it is important to extend the pure text based methods to incorporate other…

Transducer and Attention based Encoder-Decoder (AED) are two widely used frameworks for speech-to-text tasks. They are designed for different purposes and each has its own benefits and drawbacks for speech-to-text tasks. In order to…

Transformer has demonstrated its great power to learn contextual word representations for multiple languages in a single model. To process multilingual sentences in the model, a learnable vector is usually assigned to each language, which…

In the past few years, triplet loss-based metric embeddings have become a de-facto standard for several important computer vision problems, most no-tably, person reidentification. On the other hand, in the area of speech recognition the…

We investigate training end-to-end speech recognition models with the recurrent neural network transducer (RNN-T): a streaming, all-neural, sequence-to-sequence architecture which jointly learns acoustic and language model components from…

End-to-end spoken language understanding (SLU) systems that process human-human or human-computer interactions are often context independent and process each turn of a conversation independently. Spoken conversations on the other hand, are…