Related papers: LIP: Lightweight Intelligent Preprocessor for mean…
The exponential growth of social media and generative AI has transformed information dissemination, fostering connectivity but also accelerating the spread of misinformation. Understanding information propagation dynamics and developing…
CLIP is one of the most popular foundational models and is heavily used for many vision-language tasks. However, little is known about the inner workings of CLIP. To bridge this gap we propose a study to quantify the interpretability in…
Self-supervised learning (SSL) techniques have achieved remarkable results in various speech processing tasks. Nonetheless, a significant challenge remains in reducing the reliance on vast amounts of speech data for pre-training. This paper…
The fusion of speech and language in the era of large language models has garnered significant attention. Discrete speech token is often utilized in text-to-speech tasks for speech compression and portability, which is convenient for joint…
Although perception systems have made remarkable advancements in recent years, they still rely on explicit human instruction or pre-defined categories to identify the target objects before executing visual recognition tasks. Such systems…
This paper introduces a new end-to-end text-to-speech (E2E-TTS) toolkit named ESPnet-TTS, which is an extension of the open-source speech processing toolkit ESPnet. The toolkit supports state-of-the-art E2E-TTS models, including Tacotron~2,…
SMILES, a crucial textual representation of molecular structures, has garnered significant attention as a foundation for pre-trained language models (LMs). However, most existing pre-trained SMILES LMs focus solely on the single-token level…
State-of-the-art text-to-speech (TTS) systems require several hours of recorded speech data to generate high-quality synthetic speech. When using reduced amounts of training data, standard TTS models suffer from speech quality and…
Deploying large language model (LLM)-driven conversational agents in enterprise settings requires prompts that are simultaneously correct at launch and resilient to the non-deterministic behavioral drift that characterizes production LLM…
Emotion is essential in spoken communication, yet most existing frameworks in speech emotion modeling rely on predefined categories or low-dimensional continuous attributes, which offer limited expressive capacity. Recent advances in speech…
Diffusion-based Generative AI gains significant attention for its superior performance over other generative techniques like Generative Adversarial Networks and Variational Autoencoders. While it has achieved notable advancements in fields…
The front-end module in a typical Mandarin text-to-speech system (TTS) is composed of a long pipeline of text processing components, which requires extensive efforts to build and is prone to large accumulative model size and cascade errors.…
End-to-end (E2E) models are becoming increasingly popular for spoken language understanding (SLU) systems and are beginning to achieve competitive performance to pipeline-based approaches. However, recent work has shown that these models…
In this paper, we propose a novel fully automatic pipeline to generate text images that are legible and strongly aligned to the desired semantic concept taken from the users' inputs. In our method, users are able to put three inputs into…
Lipreading, i.e. speech recognition from visual-only recordings of a speaker's face, can be achieved with a processing pipeline based solely on neural networks, yielding significantly better accuracy than conventional methods. Feed-forward…
Large language models (LLMs) have shown remarkable performance in complex reasoning tasks, but their efficiency is hindered by the substantial memory and computational costs associated with generating lengthy tokens. In this paper, we…
Current text-to-speech (TTS) models face a persistent limitation: autoregressive (AR) models suffer from low generation efficiency, while modern non-autoregressive (NAR) models experience high latency due to their unordered temporal nature.…
Large-scale, pre-trained language models (LMs) have achieved human-level performance on a breadth of language understanding tasks. However, evaluations only based on end task performance shed little light on machines' true ability in…
Mobile messaging apps offer an increasing range of emotional expressions, such as emojis to help users manually augment their texting experiences. Accessibility of such augmentations is limited in voice messaging. With the term "speejis" we…
While current emotional Text-to-Speech (TTS) models have successfully controlled verbal prosody, they often ignore non-verbal vocalizations (NVs), which are essential for authentic human emotion. Although some non-verbal datasets have…