Related papers: Enhanced Speaker-aware Multi-party Multi-turn Dial…

Deep speaker embeddings have become the leading method for encoding speaker identity in speaker recognition tasks. The embedding space should ideally capture the variations between all possible speakers, encoding the multiple acoustic…

Recently, there have been attempts to integrate various speech processing tasks into a unified model. However, few previous works directly demonstrated that joint optimization of diverse tasks in multitask speech models has positive…

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…

Emotion recognition in multi-speaker conversations faces significant challenges due to speaker ambiguity and severe class imbalance. We propose a novel framework that addresses these issues through three key innovations: (1) a speaker…

Streaming multi-talker speech translation is a task that involves not only generating accurate and fluent translations with low latency but also recognizing when a speaker change occurs and what the speaker's gender is. Speaker change…

This work shows how to improve and interpret the commonly used dual encoder model for response suggestion in dialogue. We present an attentive dual encoder model that includes an attention mechanism on top of the extracted word-level…

With the continuous development of deep learning (DL), the task of multimodal dialogue emotion recognition (MDER) has recently received extensive research attention, which is also an essential branch of DL. The MDER aims to identify the…

Speaker identification, determining which character said each utterance in literary text, benefits many downstream tasks. Most existing approaches use expert-defined rules or rule-based features to directly approach this task, but these…

Informed speaker extraction aims to extract a target speech signal from a mixture of sources given prior knowledge about the desired speaker. Recent deep learning-based methods leverage a speaker discriminative model that maps a reference…

The performance of speaker verification degrades significantly when the test speech is corrupted by interference speakers. Speaker diarization does well to separate speakers if the speakers are temporally overlapped. However, if…

Sequence to sequence models attempt to capture the correlation between all the words in the input and output sequences. While this is quite useful for machine translation where the correlation among the words is indeed quite strong, it…

This paper presents a new network architecture called multi-head decoder for end-to-end speech recognition as an extension of a multi-head attention model. In the multi-head attention model, multiple attentions are calculated, and then,…

In this paper we exploit cross-lingual models to enable dialogue act recognition for specific tasks with a small number of annotations. We design a transfer learning approach for dialogue act recognition and validate it on two different…

In the era of digitalization, as individuals increasingly rely on digital platforms for communication and news consumption, various actors employ linguistic strategies to influence public perception. While models have become proficient at…

Recently, end-to-end models have become a popular approach as an alternative to traditional hybrid models in automatic speech recognition (ASR). The multi-speaker speech separation and recognition task is a central task in cocktail party…

Instruction-based speech processing is becoming popular. Studies show that training with multiple tasks boosts performance, but collecting diverse, large-scale tasks and datasets is expensive. Thus, it is highly desirable to design a…

In this work, we systematically investigate how well current models of coherence can capture aspects of text implicated in discourse organisation. We devise two datasets of various linguistic alterations that undermine coherence and test…

Large language models excel at following explicit instructions, but they often struggle with ambiguous or incomplete user requests, defaulting to verbose, generic responses instead of seeking clarification. We introduce InfoQuest, a…

Spoken dialogue systems often rely on cascaded pipelines that transcribe, process, and resynthesize speech. While effective, this design discards paralinguistic cues and limits expressivity. Recent end-to-end methods reduce latency and…

Dialogue Act (DA) classification is the task of classifying utterances with respect to the function they serve in a dialogue. Existing approaches to DA classification model utterances without incorporating the turn changes among speakers…