相关论文: Multilingual Bottleneck Features for Query by Exam…

An effective method to improve neural machine translation with monolingual data is to augment the parallel training corpus with back-translations of target language sentences. This work broadens the understanding of back-translation and…

This paper presents an improved deep embedding learning method based on convolutional neural network (CNN) for text-independent speaker verification. Two improvements are proposed for x-vector embedding learning: (1) Multi-scale convolution…

This paper presents a multi-label stuttering detection system trained on multi-corpus, multilingual data in English, German, and Mandarin.By leveraging annotated stuttering data from three languages and four corpora, the model captures…

We present Attract-Repel, an algorithm for improving the semantic quality of word vectors by injecting constraints extracted from lexical resources. Attract-Repel facilitates the use of constraints from mono- and cross-lingual resources,…

Phonetic information and linguistic knowledge are an essential component of a Text-to-speech (TTS) front-end. Given a language, a lexicon can be collected offline and Grapheme-to-Phoneme (G2P) relationships are usually modeled in order to…

Building speech recognizers in multiple languages typically involves replicating a monolingual training recipe for each language, or utilizing a multi-task learning approach where models for different languages have separate output labels…

Concept bottleneck models (CBM) aim to improve model interpretability by predicting human level "concepts" in a bottleneck within a deep learning model architecture. However, how the predicted concepts are used in predicting the target…

The recently proposed Sequence-to-Sequence (seq2seq) framework advocates replacing complex data processing pipelines, such as an entire automatic speech recognition system, with a single neural network trained in an end-to-end fashion. In…

Despite multilingual pretraining, large language models often struggle with non-English tasks, particularly in language control, the ability to respond in the intended language. We identify and characterize two key failure modes: the…

This study proposes a new way of using WordNet for Query Expansion (QE). We choose candidate expansion terms, as usual, from a set of pseudo relevant documents; however, the usefulness of these terms is measured based on their definitions…

Current disfluency detection models focus on individual utterances each from a single speaker. However, numerous discontinuity phenomena in spoken conversational transcripts occur across multiple turns, hampering human readability and the…

Keyword spotting (KWS) on mobile devices generally requires a small memory footprint. However, most current models still maintain a large number of parameters in order to ensure good performance. In this paper, we propose a temporally…

We present a deep hierarchical recurrent neural network for sequence tagging. Given a sequence of words, our model employs deep gated recurrent units on both character and word levels to encode morphology and context information, and…

Natural language-based vehicle retrieval is a task to find a target vehicle within a given image based on a natural language description as a query. This technology can be applied to various areas including police searching for a suspect…

A new language model for speech recognition inspired by linguistic analysis is presented. The model develops hidden hierarchical structure incrementally and uses it to extract meaningful information from the word history - thus enabling the…

Neural chat translation aims to translate bilingual conversational text, which has a broad application in international exchanges and cooperation. Despite the impressive performance of sentence-level and context-aware Neural Machine…

In this paper, our goal is to investigate to what degree multilingual pretrained language models capture cross-linguistically valid abstract linguistic representations. We take the approach of developing curated synthetic data on a large…

This paper describes a test collection (benchmark data) for retrieval systems driven by spoken queries. This collection was produced in the subtask of the NTCIR-3 Web retrieval task, which was performed in a TREC-style evaluation workshop.…

Multi-lingual speech recognition aims to distinguish linguistic expressions in different languages and integrate acoustic processing simultaneously. In contrast, current multi-lingual speech recognition research follows a language-aware…

We propose a new end-to-end neural acoustic model for automatic speech recognition. The model is composed of multiple blocks with residual connections between them. Each block consists of one or more modules with 1D time-channel separable…