相关论文: SpeechBERTScore: Reference-Aware Automatic Evaluat…

In this report we present a system that can generate political speeches for a desired political party. Furthermore, the system allows to specify whether a speech should hold a supportive or opposing opinion. The system relies on a…

In recent years, machine learning models have rapidly become better at generating clinical consultation notes; yet, there is little work on how to properly evaluate the generated consultation notes to understand the impact they may have on…

With the advent of high-quality speech synthesis, there is a lot of interest in controlling various prosodic attributes of speech. Speaking rate is an essential attribute towards modelling the expressivity of speech. In this work, we…

Social media has seen a worrying rise in hate speech in recent times. Branching to several distinct categories of cyberbullying, gender discrimination, or racism, the combined label for such derogatory content can be classified as toxic…

This paper presents sampling-based speech parameter generation using moment-matching networks for Deep Neural Network (DNN)-based speech synthesis. Although people never produce exactly the same speech even if we try to express the same…

Automatically evaluating the quality of language generation is critical. Although recent learned metrics show high correlation with human judgement, these metrics can not explain their verdict or associate the scores with defects in…

Cutting-edge abstractive summarisers generate fluent summaries, but the factuality of the generated text is not guaranteed. Early summary factuality evaluation metrics are usually based on n-gram overlap and embedding similarity, but are…

Existing metrics for assessing question generation not only require costly human reference but also fail to take into account the input context of generation, rendering the lack of deep understanding of the relevance between the generated…

Progress in speech processing has been facilitated by shared datasets and benchmarks. Historically these have focused on automatic speech recognition (ASR), speaker identification, or other lower-level tasks. Interest has been growing in…

This paper introduces NoRefER, a novel referenceless quality metric for automatic speech recognition (ASR) systems. Traditional reference-based metrics for evaluating ASR systems require costly ground-truth transcripts. NoRefER overcomes…

Evaluating sign language generation is often done through back-translation, where generated signs are first recognized back to text and then compared to a reference using text-based metrics. However, this two-step evaluation pipeline…

Recent advances in text-to-speech (TTS) led to the development of flexible multi-speaker end-to-end TTS systems. We extend state-of-the-art attention-based automatic speech recognition (ASR) systems with synthetic audio generated by a TTS…

Aligning large generative models with human feedback is a critical challenge. In speech synthesis, this is particularly pronounced due to the lack of a large-scale human preference dataset, which hinders the development of models that truly…

Evaluating speech generation still relies heavily on human judgments, such as Mean Opinion Score (MOS), which are expensive, subjective, and difficult to reproduce at scale. While a few recent studies have begun to explore AudioLLM-based…

In speech quality estimation for speech enhancement (SE) systems, subjective listening tests so far are considered as the gold standard. This should be even more true considering the large influx of new generative or hybrid methods into the…

Recent advances in speech language models, such as GPT-4o Voice Mode and Gemini Live, have demonstrated promising speech generation capabilities. Nevertheless, the aesthetic naturalness of the synthesized audio still lags behind that of…

Recent advances in pre-trained language models have significantly improved neural response generation. However, existing methods usually view the dialogue context as a linear sequence of tokens and learn to generate the next word through…

Since its inception, the field of deep speech enhancement has been dominated by predictive (discriminative) approaches, such as spectral mapping or masking. Recently, however, novel generative approaches have been applied to speech…

Natural language generation (NLG) is a critical component of spoken dialogue and it has a significant impact both on usability and perceived quality. Most NLG systems in common use employ rules and heuristics and tend to generate rigid and…

Recent advances in generative language modeling applied to discrete speech tokens presented a new avenue for text-to-speech (TTS) synthesis. These speech language models (SLMs), similarly to their textual counterparts, are scalable,…