Current approaches to program synthesis with Large Language Models (LLMs) exhibit a "near miss syndrome": they tend to generate programs that semantically resemble the correct answer (as measured by text similarity metrics or human evaluation), but achieve a low or even zero accuracy as measured by unit tests due to small imperfections, such as the wrong input or output format. This calls for an approach known as Synthesize, Execute, Debug (SED), whereby a draft of the solution is generated first, followed by a program repair phase addressing the failed tests. To effectively apply this approach to instruction-driven LLMs, one needs to determine which prompts perform best as instructions for LLMs, as well as strike a balance between repairing unsuccessful programs and replacing them with newly generated ones. We explore these trade-offs empirically, comparing replace-focused, repair-focused, and hybrid debug strategies, as well as different template-based and model-based prompt-generation techniques. We use OpenAI Codex as the LLM and Program Synthesis Benchmark 2 as a database of problem descriptions and tests for evaluation. The resulting framework outperforms both conventional usage of Codex without the repair phase and traditional genetic programming approaches.

Respiration is an essential and primary mechanism for speech production. We first inhale and then produce speech while exhaling. When we run out of breath, we stop speaking and inhale. Though this process is involuntary, speech production involves a systematic outflow of air during exhalation characterized by linguistic content and prosodic factors of the utterance. Thus speech and respiration are closely related, and modeling this relationship makes sensing respiratory dynamics directly from the speech plausible, however is not well explored. In this article, we conduct a comprehensive study to explore techniques for sensing breathing signal and breathing parameters from speech using deep learning architectures and address the challenges involved in establishing the practical purpose of this technology. Estimating the breathing pattern from the speech would give us information about the respiratory parameters, thus enabling us to understand the respiratory health using one's speech.

A method to detect the distance of a speaker from a single microphone in a room environment is proposed. Several features, related to statistical parameters of speech source excitation signals, are introduced and are shown to depend on the distance between source and receiver. Those features are used to train a pattern recognizer for distance detection. The method is tested using a database of speech recordings in four rooms with different acoustical properties. Performance is shown to be independent of the signal gain and level, but depends on the reverberation time and the characteristics of the room. Overall, the system performs well especially for close distances and for rooms with low reverberation time and it appears to be robust to small distance mismatches. Finally, a listening test is conducted in order to compare the results of the proposed method to the performance of human listeners.

Breathing is the primary mechanism for maintaining the subglottal pressure for speech production. Speech can be seen as a systematic outflow of air during exhalation characterized by linguistic content and prosodic factors. Thus, sensing respiratory dynamics from the speech is plausible. In this paper, we explore techniques for sensing breathing from speech using deep learning architectures including multi-task learning approaches. Estimating the breathing pattern from the speech would give us information about the respiration rate, breathing capacity and thus enable us to understand the pathological condition of a person using one’s speech. Training and evaluation of our model on our database of breathing signal and speech for 40 subjects yielded a sensitivity of 0.88 for breath event detection and 5.6 % error for breathing rate estimation.

Program synthesis with Large Language Models (LLMs) suffers from a “near-miss syndrome”: The generated code closely resembles a correct solution but fails unit tests due to minor errors. We address this with a multi-agent framework called Synthesize, Execute, Instruct, Debug, and Repair (SEIDR). Effectively applying SEIDR to instruction-tuned LLMs requires determining (a) optimal prompts for LLMs, (b) what ranking algorithm selects the best programs in debugging rounds, and (c) balancing the repair of unsuccessful programs with the generation of new ones. We empirically explore these tradeoffs by comparing replace-focused, repair-focused, and hybrid debug strategies. We also evaluate lexicase and tournament selection to rank candidates in each generation. On Program Synthesis Benchmark 2 (PSB2), our framework outperforms both conventional use of OpenAI Codex without a repair phase and traditional genetic programming approaches. SEIDR outperforms the use of an LLM alone, solving 18 problems in C++ and 20 in Python on PSB2 at least once across experiments. To assess generalizability, we employ GPT-3.5 and Llama 3 on the PSB2 and HumanEval-X benchmarks. Although SEIDR with these models does not surpass current state-of-the-art methods on the Python benchmarks, the results on HumanEval-C++ are promising. SEIDR with Llama 3-8B achieves an average pass@100 of 84.2%. Across all SEIDR runs, 163 of 164 problems are solved at least once with GPT-3.5 in HumanEval-C++, and 162 of 164 with the smaller Llama 3-8B. We conclude that SEIDR effectively overcomes the near-miss syndrome in program synthesis with LLMs.