Related papers: PolyMorph: Increasing P300 Spelling Efficiency by …
Multi-agent reinforcement learning (MARL) is well-suited for runtime decision-making in optimizing the performance of systems where multiple agents coexist and compete for shared resources. However, applying common deep learning-based MARL…
Symbolic regression is a type of discrete optimization problem that involves searching expressions that fit given data points. In many cases, other mathematical constraints about the unknown expression not only provide more information…
In this study, a novel control algorithm for a P-300 based brain-computer interface is fully developed to control a 2-DoF robotic arm. Eight subjects including 5 men and 3 women, perform a 2-dimensional target tracking task in a simulated…
Spikes are the currency in central nervous systems for information transmission and processing. They are also believed to play an essential role in low-power consumption of the biological systems, whose efficiency attracts increasing…
The Split and Rephrase (SPRP) task, which consists in splitting complex sentences into a sequence of shorter grammatical sentences, while preserving the original meaning, can facilitate the processing of complex texts for humans and…
Syntactic natural language parsers have shown themselves to be inadequate for processing highly-ambiguous large-vocabulary text, as is evidenced by their poor performance on domains like the Wall Street Journal, and by the movement away…
Large Language Models are increasingly used as zero-shot classifiers in complex reasoning tasks. However, standard constrained decoding suffers from a phenomenon we define as Renormalization Bias. When a model is restricted to a small set…
We propose a speaker selection mechanism (SSM) for the training of an end-to-end beamforming neural network, based on recent findings that a listener usually looks to the target speaker with a certain undershot angle. The mechanism allows…
This paper presents PolyIPA, a novel multilingual phoneme-to-grapheme conversion model designed for multilingual name transliteration, onomastic research, and information retrieval. The model leverages two helper models developed for data…
This work presents a novel approach for speaker diarization to leverage lexical information provided by automatic speech recognition. We propose a speaker diarization system that can incorporate word-level speaker turn probabilities with…
Template-based signal detection most often relies on computing a correlation, or a dot product, between an incoming data stream and a signal template. While such a correlation results in an ongoing estimate of the magnitude of the signal in…
The predominant metric for evaluating speech recognizers, the Word Error Rate (WER) has been extended in different ways to handle transcripts produced by long-form multi-talker speech recognizers. These systems process long transcripts…
Language model fusion helps smart assistants recognize words which are rare in acoustic data but abundant in text-only corpora (typed search logs). However, such corpora have properties that hinder downstream performance, including being…
The study presented here relies on the integrated use of different kinds of knowledge in order to improve first-guess accuracy in non-word context-sensitive correction for general unrestricted texts. State of the art spelling correction…
Acoustical mismatch among training and testing phases degrades outstandingly speech recognition results. This problem has limited the development of real-world nonspecific applications, as testing conditions are highly variant or even…
This thesis presents a broad-coverage probabilistic top-down parser, and its application to the problem of language modeling for speech recognition. The parser builds fully connected derivations incrementally, in a single pass from…
Low-resource languages (LRLs) face challenges in supervised neural machine translation due to limited parallel data, prompting research into unsupervised methods. Unsupervised neural machine translation (UNMT) methods, including…
Neural networks are among the state-of-the-art techniques for language modeling. Existing neural language models typically map discrete words to distributed, dense vector representations. After information processing of the preceding…
Although modern automatic speech recognition (ASR) systems can achieve high performance, they may produce errors that weaken readers' experience and do harm to downstream tasks. To improve the accuracy and reliability of ASR hypotheses, we…
The iterated learning model simulates the transmission of language from generation to generation in order to explore how the constraints imposed by language transmission facilitate the emergence of language structure. Despite each modelled…