Related papers: Wav2SQL: Direct Generalizable Speech-To-SQL Parsin…

There is a rising interest and trend in research towards directly translating speech from one language to another, known as end-to-end speech-to-speech translation. However, most end-to-end models struggle to outperform cascade models,…

Whispered speech lacks vocal fold vibration and fundamental frequency, resulting in degraded acoustic cues and making whisper-to-normal (W2N) conversion challenging, especially with limited parallel data. We propose WhispEar, a…

Evaluating text-to-SQL systems remains largely fragile: correctness is typically judged by executing predicted and gold SQL queries on a single static database, even though the same queries may behave differently under alternative database…

Automatic speech recognition (ASR) has gained remarkable successes thanks to recent advances of deep learning, but it usually degrades significantly under real-world noisy conditions. Recent works introduce speech enhancement (SE) as…

Text-to-SQL, the task of translating natural language questions into SQL queries, is part of various business processes. Its automation, which is an emerging challenge, will empower software practitioners to seamlessly interact with…

Real-time speech-to-speech (S2S) models excel at generating natural, low-latency conversational responses but often lack deep knowledge and semantic understanding. Conversely, cascaded systems combining automatic speech recognition, a…

Text-to-SQL translates natural language queries into Structured Query Language (SQL) commands, enabling users to interact with databases using natural language. Essentially, the text-to-SQL task is a text generation task, and its…

Recent progress in language model pre-training has achieved a great success via leveraging large-scale unstructured textual data. However, it is still a challenge to apply pre-training on structured tabular data due to the absence of…

Transforming natural language into SQL queries (NL2SQL) is crucial for data-driven business applications. Existing frameworks, trained on open-source datasets, struggle with complex business logic and lack domain-specific data for…

Time series is a special type of sequence data, a sequence of real-valued random variables collected at even intervals of time. The real-world multivariate time series comes with noises and contains complicated local and global temporal…

Direct acoustics-to-word (A2W) models in the end-to-end paradigm have received increasing attention compared to conventional sub-word based automatic speech recognition models using phones, characters, or context-dependent hidden Markov…

Text-to-SQL, the process of translating natural language into Structured Query Language (SQL), represents a transformative application of large language models (LLMs), potentially revolutionizing how humans interact with data. This paper…

While the general idea of self-supervised learning is identical across modalities, the actual algorithms and objectives differ widely because they were developed with a single modality in mind. To get us closer to general self-supervised…

The ultimate goal of expressive speech-to-speech translation (S2ST) is to accurately translate spoken content while preserving the speaker identity and emotional style. However, progress in this field is largely hindered by three key…

Text-to-SQL (Text2SQL) aims to map natural language questions to executable SQL queries. Although large language models (LLMs) have driven significant progress, current approaches struggle with poor transferability to open-source LLMs,…

Natural Language Interfaces for Databases empower non-technical users to interact with data using natural language (NL). Advanced approaches, utilizing either neural sequence-to-sequence or more recent sophisticated large-scale language…

Speech-aware language models (LMs) have demonstrated capabilities in understanding spoken language while generating text-based responses. However, enabling them to produce speech output efficiently and effectively remains a challenge. In…

Sequence-to-sequence (seq2seq) voice conversion (VC) models are attractive owing to their ability to convert prosody. Nonetheless, without sufficient data, seq2seq VC models can suffer from unstable training and mispronunciation problems in…

Real-world enterprise text-to-SQL workflows often involve complex cloud or local data across various database systems, multiple SQL queries in various dialects, and diverse operations from data transformation to analytics. We introduce…

Direct Speech-to-Speech Translation (S2ST) has gained increasing attention for its ability to translate speech from one language to another, while reducing error propagation and latency inherent in traditional cascaded pipelines. However,…