Discriminative language model adaptation for Mandarin broadcast speech transcription and translation

This paper investigates unsupervised test-time adaptation of language models (LM) using discriminative methods for a Mandarin broadcast speech transcription and translation task. A standard approach to adapt interpolated language models to is to optimize the component weights by minimizing the perplexity on supervision data. This is a widely made approximation for language modeling in automatic speech recognition (ASR) systems. For speech translation tasks, it is unclear whether a strong correlation still exists between perplexity and various forms of error cost functions in recognition and translation stages. The proposed minimum Bayes risk (MBR) based approach provides a flexible framework for unsupervised LM adaptation. It generalizes to a variety of forms of recognition and translation error metrics. LM adaptation is performed at the audio document level using either the character error rate (CER), or translation edit rate (TER) as the cost function. An efficient parameter estimation scheme using the extended Baum-Welch (EBW) algorithm is proposed. Experimental results on a state-of-the-art speech recognition and translation system are presented. The MBR adapted language models gave the best recognition and translation performance and reduced the TER score by up to 0.54% absolute. © 2007 IEEE.

158-microJ pulses from a single-transverse-mode, large-mode-area erbium-doped fiber amplifier.

We report the amplification of 10-100-pJ semiconductor diode pulses to an energy of 158 microJ and peak powers >100 kW in a multistage fiber amplifier chain based on a single-mode, large-mode-area erbium-doped amplifier design. To our knowledge these results represent the highest single-mode pulse energy extracted from any doped-fiber system.

158-μJ pulses from a single-transverse-mode, large-mode-area erbium-doped fiber amplifier

We report the amplification of 10-100-pJ semiconductor diode pulses to an energy of 158 μJ and peak powers >100 kW in a multistage fiber amplifier chain based on a single-mode, large-mode-area erbium-doped amplifier design. To our knowledge these results represent the highest single-mode pulse energy extracted from any doped-fiber system. © 1997 Optical Society of America.