相关论文: Towards Language-Universal End-to-End Speech Recog…

Preserving a speaker's voice identity while generating speech in a different language remains a fundamental challenge in spoken language technology, particularly in specialized domains such as scientific communication. In this paper, we…

Learning an efficient manager of dialogue agent from data with little manual intervention is important, especially for goal-oriented dialogues. However, existing methods either take too many manual efforts (e.g. reinforcement learning…

Multilingual generative models obtain remarkable cross-lingual in-context learning capabilities through pre-training on large-scale corpora. However, they still exhibit a performance bias toward high-resource languages and learn isolated…

In this paper, we particularly work on the code-switched text, one of the most common occurrences in the bilingual communities across the world. Due to the discrepancies in the extraction of code-switched text from an Automated Speech…

Prior work on Sign Language Translation has shown that having a mid-level sign gloss representation (effectively recognizing the individual signs) improves the translation performance drastically. In fact, the current state-of-the-art in…

End-to-end spoken language understanding (SLU) systems have many advantages over conventional pipeline systems, but collecting in-domain speech data to train an end-to-end system is costly and time consuming. One question arises from this:…

In this work, we present a hybrid CTC/Attention model based on a ResNet-18 and Convolution-augmented transformer (Conformer), that can be trained in an end-to-end manner. In particular, the audio and visual encoders learn to extract…

Existing dialog systems are all monolingual, where features shared among different languages are rarely explored. In this paper, we introduce a novel multilingual dialogue system. Specifically, we augment the sequence to sequence framework…

Whereas conventional spoken language understanding (SLU) systems map speech to text, and then text to intent, end-to-end SLU systems map speech directly to intent through a single trainable model. Achieving high accuracy with these…

Personalized dialogue systems are an essential step toward better human-machine interaction. Existing personalized dialogue agents rely on properly designed conversational datasets, which are mostly monolingual (e.g., English), which…

We train one multilingual model for dependency parsing and use it to parse sentences in several languages. The parsing model uses (i) multilingual word clusters and embeddings; (ii) token-level language information; and (iii)…

End-to-end architectures have been recently proposed for spoken language understanding (SLU) and semantic parsing. Based on a large amount of data, those models learn jointly acoustic and linguistic-sequential features. Such architectures…

We present a method for introducing a text encoder into pre-trained end-to-end speech translation systems. It enhances the ability of adapting one modality (i.e., source-language speech) to another (i.e., source-language text). Thus, the…

On-device end-to-end speech recognition poses a high requirement on model efficiency. Most prior works improve the efficiency by reducing model sizes. We propose to reduce the complexity of model architectures in addition to model sizes.…

A Pascal challenge entitled monaural multi-talker speech recognition was developed, targeting the problem of robust automatic speech recognition against speech like noises which significantly degrades the performance of automatic speech…

A new type of End-to-End system for text-dependent speaker verification is presented in this paper. Previously, using the phonetically discriminative/speaker discriminative DNNs as feature extractors for speaker verification has shown…

This paper presents a new approach for end-to-end audio-visual multi-talker speech recognition. The approach, referred to here as the visual context attention model (VCAM), is important because it uses the available video information to…

Multilingual Speech Recognition is one of the most costly AI problems, because each language (7,000+) and even different accents require their own acoustic models to obtain best recognition performance. Even though they all use the same…

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…

Spoken language recognition (SLR) is the task of automatically identifying the language present in a speech signal. Existing SLR models are either too computationally expensive or too large to run effectively on devices with limited…