Related papers: Generative linguistic representation for spoken la…

Automatic Speech Recognition (ASR) technology has made significant progress in recent years, providing accurate transcription across various domains. However, some challenges remain, especially in noisy environments and specialized jargon.…

Self-supervised learning models for speech processing, such as wav2vec2, HuBERT, WavLM, and Whisper, generate embeddings that capture both linguistic and paralinguistic information, making it challenging to analyze tone independently of…

We propose to implement speech enhancement by the regeneration of clean speech from a salient representation extracted from the noisy signal. The network that extracts salient features is trained using a set of weight-sharing clones of the…

Speech recognition systems for irregularly-spelled languages like English normally require hand-written pronunciations. In this paper, we describe a system for automatically obtaining pronunciations of words for which pronunciations are not…

A new language model for speech recognition is presented. The model develops hidden hierarchical syntactic-like structure incrementally and uses it to extract meaningful information from the word history, thus complementing the locality of…

We propose spoken sentence embeddings which capture both acoustic and linguistic content. While existing works operate at the character, phoneme, or word level, our method learns long-term dependencies by modeling speech at the sentence…

A crucial part of an accurate and reliable spoken language assessment system is the underlying ASR model. Recently, large-scale pre-trained ASR foundation models such as Whisper have been made available. As the output of these models is…

Large-scale in-the-wild speech datasets have become more prevalent in recent years due to increased interest in models that can learn useful features from unlabelled data for tasks such as speech recognition or synthesis. These datasets…

Recurrent models for sequences have been recently successful at many tasks, especially for language modeling and machine translation. Nevertheless, it remains challenging to extract good representations from these models. For instance, even…

While dense retrieval models, which embed queries and documents into a shared low-dimensional space, have gained widespread popularity, they were shown to exhibit important theoretical limitations and considerably lag behind traditional…

Humans can obtain the knowledge of novel visual concepts from language descriptions, and we thus use the few-shot image classification task to investigate whether a machine learning model can have this capability. Our proposed model, LIDE…

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…

Language Identification (LID) is a crucial preliminary process in the field of Automatic Speech Recognition (ASR) that involves the identification of a spoken language from audio samples. Contemporary systems that can process speech in…

This paper proposes a novel Wavelet Packet based feature extraction approach for the task of text independent speaker recognition. The features are extracted by using the combination of Mel Frequency Cepstral Coefficient (MFCC) and Wavelet…

Currently, a common approach in many speech processing tasks is to leverage large scale pre-trained models by fine-tuning them on in-domain data for a particular application. Yet obtaining even a small amount of such data can be…

Recent advancements in unsupervised feature learning have developed powerful latent representations of words. However, it is still not clear what makes one representation better than another and how we can learn the ideal representation.…

We present an open-source system designed for multilingual translation and speech regeneration, addressing challenges in communication and accessibility across diverse linguistic contexts. The system integrates Whisper for speech…

This paper proposes an Expressive Speech Synthesis model that utilizes token-level latent prosodic variables in order to capture and control utterance-level attributes, such as character acting voice and speaking style. Current works aim to…

Cross-lingual alignment in pretrained language models enables knowledge transfer across languages. Similar alignment has been reported in Whisper-style speech encoders, based on spoken translation retrieval using representational…

Existing large language model (LLM)-based embeddings typically adopt an encoder-only paradigm, treating LLMs as static feature extractors and overlooking their core generative strengths. We introduce GIRCSE (Generative Iterative Refinement…