Related papers: Can Sequence-to-Sequence Models Crack Substitution…
Acoustic-to-Word recognition provides a straightforward solution to end-to-end speech recognition without needing external decoding, language model re-scoring or lexicon. While character-based models offer a natural solution to the…
Machine learning techniques have proved useful for classifying and analyzing audio content. However, recent methods typically rely on abstract and high-dimensional representations that are difficult to interpret. Inspired by…
Recently it was shown that permutation-only multimedia ciphers can completely be broken in a chosen-plaintext scenario. Apparently, chosen-plaintext scenario models a very resourceful adversary and does not hold in many practical…
We investigate the problem of transforming an input sequence into a high-dimensional output sequence in order to transcribe polyphonic audio music into symbolic notation. We introduce a probabilistic model based on a recurrent neural…
Large Language Models (LLMs) are revolutionizing how users interact with information systems, yet their high inference cost poses serious scalability and sustainability challenges. Caching inference responses, allowing them to be retrieved…
To scale neural speech synthesis to various real-world languages, we present a multilingual end-to-end framework that maps byte inputs to spectrograms, thus allowing arbitrary input scripts. Besides strong results on 40+ languages, the…
The ability to match pieces of code to their corresponding natural language descriptions and vice versa is fundamental for natural language search interfaces to software repositories. In this paper, we propose a novel multi-perspective…
Sequence to sequence (SEQ2SEQ) models often lack diversity in their generated translations. This can be attributed to the limitation of SEQ2SEQ models in capturing lexical and syntactic variations in a parallel corpus resulting from…
We present a simple cross-lingual plagiarism detection method applicable to a large number of languages. The presented approach leverages open multilingual thesauri for candidate retrieval task and pre-trained multilingual BERT-based…
Human and model-generated texts can be distinguished by examining the magnitude of likelihood in language. However, it is becoming increasingly difficult as language model's capabilities of generating human-like texts keep evolving. This…
Tokenising continuous speech into sequences of discrete tokens and modelling them with language models (LMs) has led to significant success in text-to-speech (TTS) synthesis. Although these models can generate speech with high quality and…
Crafting adversarial examples has become an important technique to evaluate the robustness of deep neural networks (DNNs). However, most existing works focus on attacking the image classification problem since its input space is continuous…
There has been increasing interest in building multilingual foundation models for NLP and speech research. This paper examines how to expand the speech translation capability of these models with restricted data. Whisper, a speech…
Text normalization is an important enabling technology for several NLP tasks. Recently, neural-network-based approaches have outperformed well-established models in this task. However, in languages other than English, there has been little…
Semantic matching is of central importance to many natural language tasks \cite{bordes2014semantic,RetrievalQA}. A successful matching algorithm needs to adequately model the internal structures of language objects and the interaction…
Cross-lingual alignment in pretrained language models enables knowledge transfer across languages. Similar alignment has been reported in Whisper-style speech encoders, based on spoken translation retrieval using representational…
Style is ubiquitous in our daily language uses, while what is language style to learning machines? In this paper, by exploiting the second-order statistics of semantic vectors of different corpora, we present a novel perspective on this…
While sequence-to-sequence (seq2seq) models achieve state-of-the-art performance in many natural language processing tasks, they can be too slow for real-time applications. One performance bottleneck is predicting the most likely next token…
In a controlled experiment of sequence-to-sequence approaches for the task of sentence correction, we find that character-based models are generally more effective than word-based models and models that encode subword information via…
The traditional adaptive algorithms will face the non-uniqueness problem when dealing with stereophonic acoustic echo cancellation (SAEC). In this paper, we first propose an efficient multi-input and multi-output (MIMO) scheme based on deep…