Related papers: Speaker-change Aware CRF for Dialogue Act Classifi…

We propose a neuralized undirected graphical model called Neural-Hidden-CRF to solve the weakly-supervised sequence labeling problem. Under the umbrella of probabilistic undirected graph theory, the proposed Neural-Hidden-CRF embedded with…

Domain adaptation is often hampered by exceedingly small target datasets and inaccessible source data. These conditions are prevalent in speech verification, where privacy policies and/or languages with scarce speech resources limit the…

We apply sequence-to-sequence model to mitigate the impact of speech recognition errors on open domain end-to-end dialog generation. We cast the task as a domain adaptation problem where ASR transcriptions and original text are in two…

We consider a multilingual weakly supervised learning scenario where knowledge from annotated corpora in a resource-rich language is transferred via bitext to guide the learning in other languages. Past approaches project labels across…

Spoken language understanding, which extracts intents and/or semantic concepts in utterances, is conventionally formulated as a post-processing of automatic speech recognition. It is usually trained with oracle transcripts, but needs to…

Conditional random fields (CRF) for label decoding has become ubiquitous in sequence labeling tasks. However, the local label dependencies and inefficient Viterbi decoding have always been a problem to be solved. In this work, we introduce…

Traditional speech separation and speaker diarization approaches rely on prior knowledge of target speakers or a predetermined number of participants in audio signals. To address these limitations, recent advances focus on developing…

Context-aware processing mechanisms have increasingly become a critical area of exploration for improving the semantic and contextual capabilities of language generation models. The Context-Aware Semantic Recomposition Mechanism (CASRM) was…

Speaker change detection (SCD) is an important task in dialog modeling. Our paper addresses the problem of text-based SCD, which differs from existing audio-based studies and is useful in various scenarios, for example, processing dialog…

Spoken language understanding (SLU) acts as a critical component in goal-oriented dialog systems. It typically involves identifying the speakers intent and extracting semantic slots from user utterances, which are known as intent detection…

This study examines domain effects in speaker diarization for African-accented English. We evaluate multiple production and open systems on general and clinical dialogues under a strict DER protocol that scores overlap. A consistent domain…

For several purposes in Natural Language Processing (NLP), such as Information Extraction, Sentiment Analysis or Chatbot, Named Entity Recognition (NER) holds an important role as it helps to determine and categorize entities in text into…

Speaker-attributed automatic speech recognition (ASR) in multi-speaker environments remains a significant challenge, particularly when systems conditioned on speaker embeddings fail to generalize to unseen speakers. In this work, we propose…

Conditional Random Fields (CRFs) constitute a popular and efficient approach for supervised sequence labelling. CRFs can cope with large description spaces and can integrate some form of structural dependency between labels. In this…

Spoken question answering (SQA) is challenging due to complex reasoning on top of the spoken documents. The recent studies have also shown the catastrophic impact of automatic speech recognition (ASR) errors on SQA. Therefore, this work…

Recent works show that discourse analysis benefits from modeling intra- and inter-sentential levels separately, where proper representations for text units of different granularities are desired to capture both the meaning of text units and…

Dialogue Act (DA) tagging is crucial for spoken language understanding systems, as it provides a general representation of speakers' intents, not bound to a particular dialogue system. Unfortunately, publicly available data sets with DA…

Spoken language understanding (SLU) is an essential component in conversational systems. Most SLU component treats each utterance independently, and then the following components aggregate the multi-turn information in the separate phases.…

Despite recent advances, Automatic Speech Recognition (ASR) systems are still far from perfect. Typical errors include acronyms, named entities, and domain-specific special words for which little or no labeled data is available. To address…

Automatic speech recognition systems have been largely improved in the past few decades and current systems are mainly hybrid-based and end-to-end-based. The recently proposed CTC-CRF framework inherits the data-efficiency of the hybrid…