Related papers: Closed-Form Word Error Rate Analysis for Successiv…
In 1-bit compressed sensing, the aim is to estimate a $k$-sparse unit vector $x\in S^{n-1}$ within an $\epsilon$ error (in $\ell_2$) from minimal number of linear measurements that are quantized to just their signs, i.e., from measurements…
In this article, we propose an improved multiple feedback successive interference cancellation (IMF-SIC) algorithm for symbol vector detection in multiple-input multiple-output (MIMO) spatial multiplexing systems. The multiple feedback (MF)…
We propose a modular pipeline for the single-channel separation, recognition, and diarization of meeting-style recordings and evaluate it on the Libri-CSS dataset. Using a Continuous Speech Separation (CSS) system with a TF-GridNet…
We investigate error propagation in sliding window decoding of braided convolutional codes (BCCs). Previous studies of BCCs have focused on iterative decoding thresholds, minimum distance properties, and their bit error rate (BER)…
Provable lower bounds are presented for the information rate I(X; X+S+N) where X is the symbol drawn independently and uniformly from a finite-size alphabet, S is a discrete-valued random variable (RV) and N is a Gaussian RV. It is well…
Hybrid Autoregressive Transducer (HAT) is a recently proposed end-to-end acoustic model that extends the standard Recurrent Neural Network Transducer (RNN-T) for the purpose of the external language model (LM) fusion. In HAT, the blank…
The success of the multilingual automatic speech recognition systems empowered many voice-driven applications. However, measuring the performance of such systems remains a major challenge, due to its dependency on manually transcribed…
We present a new method for computing ASR word confidences that effectively mitigates the effect of ASR errors for diverse downstream applications, improves the word error rate of the 1-best result, and allows better comparison of scores…
Successive Interference Cancellation (SIC) is a powerful technique for managing interference in wireless networks, yet its optimal deployment in decentralized environments remains a challenge. This study investigates joint power and rate…
Convexity properties of error rates of a class of decoders, including the ML/min-distance one as a special case, are studied for arbitrary constellations, bit mapping and coding. Earlier results obtained for the AWGN channel are extended to…
Many automatic speech recognition (ASR) data sets include a single pre-defined test set consisting of one or more speakers whose speech never appears in the training set. This "hold-speaker(s)-out" data partitioning strategy, however, may…
A key initial step in several natural language processing (NLP) tasks involves embedding phrases of text to vectors of real numbers that preserve semantic meaning. To that end, several methods have been recently proposed with impressive…
The maximum information rates for bandlimited channels with direct detection are achieved with joint detection and decoding (JDD), but JDD is often too complex to implement. Two receiver structures are studied to reduce complexity: separate…
Spatial mixture model (SMM) supported acoustic beamforming has been extensively used for the separation of simultaneously active speakers. However, it has hardly been considered for the separation of meeting data, that are characterized by…
Recent advances in speech foundation models are largely driven by scaling both model size and data, enabling them to perform a wide range of tasks, including speech recognition. Traditionally, ASR models are evaluated using metrics like…
In most error correction coding (ECC) frameworks, the typical error metric is the bit error rate (BER) which measures the number of bit errors. For this metric, the positions of the bits are not relevant to the decoding, and in many noise…
This paper presents a semantic-enhanced receiver framework for transmitting natural language sentences over noisy wireless channels using multiple short block codes. After ASCII encoding, the sentence is divided into segments, each…
In this correspondence, we consider an amplify-and-forward relay network in which relayed information is overheard by an eavesdropper. In order to confound the eavesdropper, a wireless-powered jammer is also considered which harvests energy…
Self-supervised learning (SSL) methods such as WavLM have shown promising speech separation (SS) results in small-scale simulation-based experiments. In this work, we extend the exploration of the SSL-based SS by massively scaling up both…
In the area of basic and network coded cooperative communication, the expected end-to-end bit error rate (BER) values are frequently required to compare the proposed coding, relaying, and decoding techniques. Instead of obtaining these…