Related papers: Addressing Cold Start Problem for End-to-end Autom…

Incorporating longer context has been shown to benefit machine translation, but the inclusion of context in end-to-end speech translation (E2E-ST) remains under-studied. To bridge this gap, we introduce target language context in E2E-ST,…

For many recommender systems, the primary data source is a historical record of user clicks. The associated click matrix is often very sparse, as the number of users x products can be far larger than the number of clicks. Such sparsity is…

Large language models have demonstrated exceptional capabilities in tasks involving natural language generation, reasoning, and comprehension. This study aims to construct prompts and comments grounded in the diverse scoring criteria…

This paper describes the submission to the IWSLT 2021 offline speech translation task by the UPC Machine Translation group. The task consists of building a system capable of translating English audio recordings extracted from TED talks into…

Text-to-speech (TTS) acoustic models map linguistic features into an acoustic representation out of which an audible waveform is generated. The latest and most natural TTS systems build a direct mapping between linguistic and waveform…

Conversational context information, higher-level knowledge that spans across sentences, can help to recognize a long conversation. However, existing speech recognition models are typically built at a sentence level, and thus it may not…

Speech Emotion Recognition (SER) is a crucial component in developing general-purpose AI agents capable of natural human-computer interaction. However, building robust multilingual SER systems remains challenging due to the scarcity of…

Automation of on-call customer support relies heavily on accurate and efficient speech-to-intent (S2I) systems. Building such systems using multi-component pipelines can pose various challenges because they require large annotated datasets,…

Modern systems that rely on Machine Learning (ML) for predictive modelling, may suffer from the cold-start problem: supervised models work well but, initially, there are no labels, which are costly or slow to obtain. This problem is even…

This paper improves contrastive learning for sentence embeddings from two perspectives: handling dropout noise and addressing feature corruption. Specifically, for the first perspective, we identify that the dropout noise from negative…

In this article we propose a novel approach for adapting speaker embeddings to new domains based on adversarial training of neural networks. We apply our embeddings to the task of text-independent speaker verification, a challenging,…

Teleconferencing is becoming essential during the COVID-19 pandemic. However, in real-world applications, speech quality can deteriorate due to, for example, background interference, noise, or reverberation. To solve this problem, target…

As Automated Essay Scoring (AES) systems are increasingly used in high-stakes educational settings, concerns regarding algorithmic bias against English as a Second Language (ESL) learners have increased. Current Transformer-based regression…

Previous work has established that a person's demographics and speech style affect how well speech processing models perform for them. But where does this bias come from? In this work, we present the Speech Embedding Association Test…

Entrainment is the phenomenon by which an interlocutor adapts their speaking style to align with their partner in conversations. It has been found in different dimensions as acoustic, prosodic, lexical or syntactic. In this work, we explore…

Sentence completion (SC) questions present a sentence with one or more blanks that need to be filled in, three to five possible words or phrases as options. SC questions are widely used for students learning English as a Second Language…

Automated Essay Scoring (AES) plays a crucial role in education by providing scalable and efficient assessment tools. However, in real-world settings, the extreme scarcity of labeled data severely limits the development and practical…

Automatic speech recognition (ASR) systems degrade significantly under noisy conditions. Recently, speech enhancement (SE) is introduced as front-end to reduce noise for ASR, but it also suppresses some important speech information, i.e.,…

Embedding acoustic information into fixed length representations is of interest for a whole range of applications in speech and audio technology. Two novel unsupervised approaches to generate acoustic embeddings by modelling of acoustic…

End-to-end (E2E) automatic speech recognition (ASR) methods exhibit remarkable performance. However, since the performance of such methods is intrinsically linked to the context present in the training data, E2E-ASR methods do not perform…