Related papers: pch2csd: an application for converting Nord Modula…
With the rise of globalisation, code-switching (CSW) has become a ubiquitous part of multilingual conversation, posing new challenges for natural language processing (NLP), especially in Grammatical Error Correction (GEC). This work…
Scalability and efficiency are desired in neural speech codecs, which supports a wide range of bitrates for applications on various devices. We propose a collaborative quantization (CQ) scheme to jointly learn the codebook of LPC…
We develop a two-part reconstruction framework for signal recovery in compressed sensing (CS), where a fast algorithm is applied to provide partial recovery in Part 1, and a CS algorithm is applied to complete the residual problem in Part…
Commutativity reasoning based on Lipton's movers is a powerful technique for verification of concurrent programs. The idea is to define a program transformation that preserves a subset of the initial set of interleavings, which is sound…
A generalized approach for the implementation of memristive two-terminal circuits with piesewise-smooth characteristics is proposed on the example of a multifunctional circuit based on a transistor switch. Two versions of the circuit are…
This paper introduces a novel voice conversion (VC) model, guided by text instructions such as "articulate slowly with a deep tone" or "speak in a cheerful boyish voice". Unlike traditional methods that rely on reference utterances to…
Overdecomposition has emerged as a powerful and sometimes essential technique in parallel programming. Many application domains or frameworks, including those based on adaptive mesh refinements, or tree codes use it. Charm++ is a parallel…
In this report, we describe the speaker diarization (SD) and language diarization (LD) systems developed by our team for the Second DISPLACE Challenge, 2024. Our contributions were dedicated to Track 1 for SD and Track 2 for LD in…
We present a neural speech codec that challenges the need for complex residual vector quantization (RVQ) stacks by introducing a simpler, single-stage quantization approach. Our method operates directly on the mel-spectrogram, treating it…
Guessing Codeword Decoding (GCD) is a recently proposed soft-input forward error correction decoder for arbitrary binary linear codes. Inspired by recent proposals that leverage binary linear codebook structure to reduce the number of…
The correctness of compilers is instrumental in the safety and reliability of other software systems, as bugs in compilers can produce executables that do not reflect the intent of programmers. Such errors are difficult to identify and…
As deep speech enhancement algorithms have recently demonstrated capabilities greatly surpassing their traditional counterparts for suppressing noise, reverberation and echo, attention is turning to the problem of packet loss concealment…
Large generative language models have been very successful for English, but other languages lag behind, in part due to data and computational limitations. We propose a method that may overcome these problems by adapting existing pre-trained…
Acoustic echo and background noise can seriously degrade the intelligibility of speech. In practice, echo and noise suppression are usually treated as two separated tasks and can be removed with various digital signal processing (DSP) and…
High-performance computing are based more and more in heterogeneous architectures and GPGPUs have become one of the main integrated blocks in these, as the recently emerged Mali GPU in embedded systems or the NVIDIA GPUs in HPC servers. In…
Code-Switching (CS) is referred to the phenomenon of alternately using words and phrases from different languages. While today's neural end-to-end (E2E) models deliver state-of-the-art performances on the task of automatic speech…
Text-to-Speech synthesis in Indian languages has a seen lot of progress over the decade partly due to the annual Blizzard challenges. These systems assume the text to be written in Devanagari or Dravidian scripts which are nearly phonemic…
Over the past few years, dictionary learning (DL)-based methods have been successfully used in various image reconstruction problems. However, traditional DL-based computed tomography (CT) reconstruction methods are patch-based and ignore…
We present a scalable and efficient neural waveform coding system for speech compression. We formulate the speech coding problem as an autoencoding task, where a convolutional neural network (CNN) performs encoding and decoding as a neural…
Ensembling certifiably robust neural networks is a promising approach for improving the \emph{certified robust accuracy} of neural models. Black-box ensembles that assume only query-access to the constituent models (and their robustness…