Related papers: Recognize Foreign Low-Frequency Words with Similar…

We present a Character-Word Long Short-Term Memory Language Model which both reduces the perplexity with respect to a baseline word-level language model and reduces the number of parameters of the model. Character information can reveal…

This paper addresses spoken language identification (SLI) and speech recognition of multilingual broadcast and institutional speech, real application scenarios that have been rarely addressed in the SLI literature. Observing that in these…

Contextual automatic speech recognition (ASR) systems allow for recognizing out-of-vocabulary (OOV) words, such as named entities or rare words. However, it remains challenging due to limited training data and ambiguous or inconsistent…

Automatic speech recognition (ASR) systems are known to be sensitive to the sociolinguistic variability of speech data, in which gender plays a crucial role. This can result in disparities in recognition accuracy between male and female…

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…

We propose a model of the speech perception of individual words in the presence of mishearings. This phenomenological approach is based on concepts used in linguistics, and provides a formalism that is universal across languages. We put…

Multi-speaker automatic speech recognition (MS-ASR) faces significant challenges in transcribing overlapped speech, a task critical for applications like meeting transcription and conversational analysis. While serialized output training…

Neural network pruning compresses automatic speech recognition (ASR) models effectively. However, in multilingual ASR, language-agnostic pruning may lead to severe performance drops on some languages because language-agnostic pruning masks…

Code-switching (CS) phenomenon occurs when words or phrases from different languages are alternated in a single sentence. Due to data scarcity, building an effective CS Automatic Speech Recognition (ASR) system remains challenging. In this…

Speech Recognition has seen a dramatic shift towards adopting Large Language Models (LLMs). This shift is partly driven by good scalability properties demonstrated by LLMs, ability to leverage large amounts of labelled, unlabelled speech…

Relation classification (RC) task is one of fundamental tasks of information extraction, aiming to detect the relation information between entity pairs in unstructured natural language text and generate structured data in the form of…

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…

Multilingual Automated Speech Recognition (ASR) systems allow for the joint training of data-rich and data-scarce languages in a single model. This enables data and parameter sharing across languages, which is especially beneficial for the…

Many automatic speech recognition (ASR) data sets include a single pre-defined test set consisting of one or more speakers whose speech never appears in the training set. This "hold-speaker(s)-out" data partitioning strategy, however, may…

Homophone characters are common in tonal syllable-based languages, such as Mandarin and Cantonese. The data-intensive end-to-end Automatic Speech Recognition (ASR) systems are more likely to mis-recognize homophone characters and rare words…

Automatic Speech Recognition (ASR) plays an important role in speech-based automatic detection of Alzheimer's disease (AD). However, recognition errors could propagate downstream, potentially impacting the detection decisions. Recent…

The conventional natural language processing approaches are not accustomed to the social media text due to colloquial discourse and non-homogeneous characteristics. Significantly, the language identification in a multilingual document is…

To effectively perform the task of next-word prediction, long short-term memory networks (LSTMs) must keep track of many types of information. Some information is directly related to the next word's identity, but some is more secondary…

The widespread usage of latent language representations via pre-trained language models (LMs) suggests that they are a promising source of structured knowledge. However, existing methods focus only on a single object per subject-relation…

Speech recognition (ASR) and speaker diarization (SD) models have traditionally been trained separately to produce rich conversation transcripts with speaker labels. Recent advances have shown that joint ASR and SD models can learn to…