相关论文: A Comparative Study of Speaker Role Identification…

Despite the close relationship between speech perception and production, research in automatic speech recognition (ASR) and text-to-speech synthesis (TTS) has progressed more or less independently without exerting much mutual influence on…

Thanks to the latest deep learning algorithms, silent speech interfaces (SSI) are now able to synthesize intelligible speech from articulatory movement data under certain conditions. However, the resulting models are rather…

Audio-visual automatic speech recognition is a promising approach to robust ASR under noisy conditions. However, up until recently it had been traditionally studied in isolation assuming the video of a single speaking face matches the…

Streaming recognition of multi-talker conversations has so far been evaluated only for 2-speaker single-turn sessions. In this paper, we investigate it for multi-turn meetings containing multiple speakers using the Streaming Unmixing and…

Although automatic emotion recognition (AER) has recently drawn significant research interest, most current AER studies use manually segmented utterances, which are usually unavailable for dialogue systems. This paper proposes integrating…

Benchmarks for language-guided embodied agents typically assume text-based instructions, but deployed agents will encounter spoken instructions. While Automatic Speech Recognition (ASR) models can bridge the input gap, erroneous ASR…

In a pipeline speech translation system, automatic speech recognition (ASR) system will transmit errors in recognition to the downstream machine translation (MT) system. A standard machine translation system is usually trained on parallel…

Speaker recognition, recognizing speaker identities based on voice alone, enables important downstream applications, such as personalization and authentication. Learning speaker representations, in the context of supervised learning,…

We extend the frameworks of Serialized Output Training (SOT) to address practical needs of both streaming and offline automatic speech recognition (ASR) applications. Our approach focuses on balancing latency and accuracy, catering to…

Bootstrapping speech recognition on limited data resources has been an area of active research for long. The recent transition to all-neural models and end-to-end (E2E) training brought along particular challenges as these models are known…

Topic classification systems on spoken documents usually consist of two modules: an automatic speech recognition (ASR) module to convert speech into text and a text topic classification (TTC) module to predict the topic class from the…

We address the problem of speech act recognition (SAR) in asynchronous conversations (forums, emails). Unlike synchronous conversations (e.g., meetings, phone), asynchronous domains lack large labeled datasets to train an effective SAR…

Multi-party dialogue machine reading comprehension (MRC) brings tremendous challenge since it involves multiple speakers at one dialogue, resulting in intricate speaker information flows and noisy dialogue contexts. To alleviate such…

Automatic Cued Speech Recognition (ACSR) provides an intelligent human-machine interface for visual communications, where the Cued Speech (CS) system utilizes lip movements and hand gestures to code spoken language for hearing-impaired…

Under noisy conditions, automatic speech recognition (ASR) can greatly benefit from the addition of visual signals coming from a video of the speaker's face. However, when multiple candidate speakers are visible this traditionally requires…

Multi-talker speech recognition (MTASR) faces unique challenges in disentangling and transcribing overlapping speech. To address these challenges, this paper investigates the role of Connectionist Temporal Classification (CTC) in speaker…

Multimodal emotion recognition from speech is an important area in affective computing. Fusing multiple data modalities and learning representations with limited amounts of labeled data is a challenging task. In this paper, we explore the…

Speech enhancement (SE) is used as a frontend in speech applications including automatic speech recognition (ASR) and telecommunication. A difficulty in using the SE frontend is that the appropriate noise reduction level differs depending…

Speech forensic tasks (SFTs), such as automatic speaker recognition (ASR), speech emotion recognition (SER), gender recognition (GR), and age estimation (AE), find use in different security and biometric applications. Previous works have…

Active speaker detection (ASD) systems are important modules for analyzing multi-talker conversations. They aim to detect which speakers or none are talking in a visual scene at any given time. Existing research on ASD does not agree on the…