Related papers: N-Best ASR Transformer: Enhancing SLU Performance …
For automatic speech translation (AST), end-to-end approaches are outperformed by cascaded models that transcribe with automatic speech recognition (ASR), then translate with machine translation (MT). A major cause of the performance gap is…
Recent advancement in deep learning encouraged developing large automatic speech recognition (ASR) models that achieve promising results while ignoring computational and memory constraints. However, deploying such models on low resource…
This paper presents a newly developed, simultaneous neural speech-to-speech translation system and its evaluation. The system consists of three fully-incremental neural processing modules for automatic speech recognition (ASR), machine…
Although Transformers have gained success in several speech processing tasks like spoken language understanding (SLU) and speech translation (ST), achieving online processing while keeping competitive performance is still essential for…
Automatic Speech Recognition (ASR), as the assistance of speech communication between pilots and air-traffic controllers, can significantly reduce the complexity of the task and increase the reliability of transmitted information. ASR…
Automatic speech recognition (ASR) is a crucial tool for linguists aiming to perform a variety of language documentation tasks. However, modern ASR systems use data-hungry transformer architectures, rendering them generally unusable for…
We present a modular approach to building cascade speech translation (AST) models that guarantees that the resulting model performs no worse than the 1-best cascade baseline while preserving state-of-the-art speech recognition (ASR) and…
Automatic speech recognition (ASR) has progressed significantly in recent years due to the emergence of large-scale datasets and the self-supervised learning (SSL) paradigm. However, as its counterpart problem in the singing domain, the…
Modern Automatic Speech Recognition (ASR) systems can achieve high performance in terms of recognition accuracy. However, a perfectly accurate transcript still can be challenging to read due to disfluency, filter words, and other errata…
Interpretability methods have recently gained significant attention, particularly in the context of large language models, enabling insights into linguistic representations, error detection, and model behaviors such as hallucinations and…
End-to-end spoken language understanding (SLU) predicts intent directly from audio using a single model. It promises to improve the performance of assistant systems by leveraging acoustic information lost in the intermediate textual…
The recent emergence of joint CTC-Attention model shows significant improvement in automatic speech recognition (ASR). The improvement largely lies in the modeling of linguistic information by decoder. The decoder joint-optimized with an…
Recent studies have made some progress in refining end-to-end (E2E) speech recognition encoders by applying Connectionist Temporal Classification (CTC) loss to enhance named entity recognition within transcriptions. However, these methods…
Automatic speech recognition (ASR) systems generate real-time transcriptions but often miss nuances that human interpreters capture. While ASR is useful in many contexts, interpreters-who already use ASR tools such as Dragon-add critical…
The Spoken Language Translator is a prototype for practically useful systems capable of translating continuous spoken language within restricted domains. The prototype system translates air travel (ATIS) queries from spoken English to…
Building Spoken Language Understanding (SLU) systems that do not rely on language specific Automatic Speech Recognition (ASR) is an important yet less explored problem in language processing. In this paper, we present a comparative study…
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…
Automatic speech recognition (ASR) is widely used in consumer electronics. ASR greatly improves the utility and accessibility of technology, but usually the output is only word sequences without punctuation. This can result in ambiguity in…
Neural models have yielded state-of-the-art results in deciphering spoken language understanding (SLU) problems; however, these models require a significant amount of domain-specific labeled examples for training, which is prohibitively…
In the domain of air traffic control (ATC) systems, efforts to train a practical automatic speech recognition (ASR) model always faces the problem of small training samples since the collection and annotation of speech samples are expert-…