shithub: opus

--- a/doc/draft-ietf-codec-opus-update.xml

+++ b/doc/draft-ietf-codec-opus-update.xml

@@ -10,7 +10,7 @@

 <?rfc inline="yes"?>

 <?rfc compact="yes"?>

 <?rfc subcompact="no"?>

-<rfc category="std" docName="draft-ietf-codec-opus-update-00"

+<rfc category="std" docName="draft-ietf-codec-opus-update-01"

      ipr="trust200902">

   <front>

     <title abbrev="Opus Update">Updates to the Opus Audio Codec</title>

@@ -19,7 +19,7 @@

 <organization>Mozilla Corporation</organization>

 <address>

 <postal>

-<street>650 Castro Street</street>

+<street>331 E. Evelyn Avenue</street>

 <city>Mountain View</city>

 <region>CA</region>

 <code>94041</code>

@@ -47,7 +47,7 @@

-    <date day="13" month="January" year="2014" />

+    <date day="4" month="September" year="2014" />

     <abstract>

       <t>This document addresses minor issues that were found in the specification

@@ -132,8 +132,8 @@

          by a compressed packet more than about 16 MB long, so it's not a problem

          for RTP. In theory, it <spanx style="emph">could</spanx> crash a file

          decoder (e.g. Opus in Ogg) if the memory just after the incoming packet

-         is out-of-range, but that could not be achieved when attempted in a production

-         application built using an affected version of the Opus decoder.</t>

+         is out-of-range, but our attempts to trigger such a crash in a production

+         application built using an affected version of the Opus decoder failed.</t>

     </section>

     <section anchor="resampler" title="Resampler buffer">

@@ -160,20 +160,22 @@

     <t>The code can be fixed by applying the following changes to line 70 of silk/resampler_private_IIR_FIR.c:

 <figure>

 <artwork><![CDATA[

-     opus_int16                      out[],          /* O    Output signal               */

-     const opus_int16                in[],           /* I    Input signal                */

-     opus_int32                      inLen           /* I    Number of input samples     */

-     silk_resampler_state_struct *S = (silk_resampler_state_struct *)SS;

+     silk_resampler_state_struct *S = \

+(silk_resampler_state_struct *)SS;

      opus_int32 nSamplesIn;

      opus_int32 max_index_Q16, index_increment_Q16;

--    opus_int16 buf[ RESAMPLER_MAX_BATCH_SIZE_IN + RESAMPLER_ORDER_FIR_12 ];

-+    opus_int16 buf[ 2*RESAMPLER_MAX_BATCH_SIZE_IN + RESAMPLER_ORDER_FIR_12 ];

+-    opus_int16 buf[ RESAMPLER_MAX_BATCH_SIZE_IN + \

+RESAMPLER_ORDER_FIR_12 ];

++    opus_int16 buf[ 2*RESAMPLER_MAX_BATCH_SIZE_IN + \

+RESAMPLER_ORDER_FIR_12 ];

      /* Copy buffered samples to start of buffer */

--    silk_memcpy( buf, S->sFIR, RESAMPLER_ORDER_FIR_12 * sizeof( opus_int32 ) );

-+    silk_memcpy( buf, S->sFIR, RESAMPLER_ORDER_FIR_12 * sizeof( opus_int16 ) );

+-    silk_memcpy( buf, S->sFIR, RESAMPLER_ORDER_FIR_12 \

+* sizeof( opus_int32 ) );

++    silk_memcpy( buf, S->sFIR, RESAMPLER_ORDER_FIR_12 \

+* sizeof( opus_int16 ) );

      /* Iterate over blocks of frameSizeIn input samples */

      index_increment_Q16 = S->invRatio_Q16;

@@ -181,28 +183,43 @@

          nSamplesIn = silk_min( inLen, S->batchSize );

          /* Upsample 2x */

-         silk_resampler_private_up2_HQ( S->sIIR, &buf[ RESAMPLER_ORDER_FIR_12 ], in, nSamplesIn );

+         silk_resampler_private_up2_HQ( S->sIIR, &buf[ \

+RESAMPLER_ORDER_FIR_12 ], in, nSamplesIn );

-         max_index_Q16 = silk_LSHIFT32( nSamplesIn, 16 + 1 );         /* + 1 because 2x upsampling */

-         out = silk_resampler_private_IIR_FIR_INTERPOL( out, buf, max_index_Q16, index_increment_Q16 );

+         max_index_Q16 = silk_LSHIFT32( nSamplesIn, 16 + 1 \

+);         /* + 1 because 2x upsampling */

+         out = silk_resampler_private_IIR_FIR_INTERPOL( out, \

+buf, max_index_Q16, index_increment_Q16 );

          in += nSamplesIn;

          inLen -= nSamplesIn;

          if( inLen > 0 ) {

-             /* More iterations to do; copy last part of filtered signal to beginning of buffer */

--            silk_memcpy( buf, &buf[ nSamplesIn << 1 ], RESAMPLER_ORDER_FIR_12 * sizeof( opus_int32 ) );

-+            silk_memmove( buf, &buf[ nSamplesIn << 1 ], RESAMPLER_ORDER_FIR_12 * sizeof( opus_int16 ) );

+             /* More iterations to do; copy last part of \

+filtered signal to beginning of buffer */

+-            silk_memcpy( buf, &buf[ nSamplesIn << 1 ], \

+RESAMPLER_ORDER_FIR_12 * sizeof( opus_int32 ) );

++            silk_memmove( buf, &buf[ nSamplesIn << 1 ], \

+RESAMPLER_ORDER_FIR_12 * sizeof( opus_int16 ) );

          } else {

              break;

-     /* Copy last part of filtered signal to the state for the next call */

--    silk_memcpy( S->sFIR, &buf[ nSamplesIn << 1 ], RESAMPLER_ORDER_FIR_12 * sizeof( opus_int32 ) );

-+    silk_memcpy( S->sFIR, &buf[ nSamplesIn << 1 ], RESAMPLER_ORDER_FIR_12 * sizeof( opus_int16 ) );

+     /* Copy last part of filtered signal to the state for \

+the next call */

+-    silk_memcpy( S->sFIR, &buf[ nSamplesIn << 1 ], \

+RESAMPLER_ORDER_FIR_12 * sizeof( opus_int32 ) );

++    silk_memcpy( S->sFIR, &buf[ nSamplesIn << 1 ], \

+RESAMPLER_ORDER_FIR_12 * sizeof( opus_int16 ) );

 ]]></artwork>

 </figure>

+    Note: due to RFC formatting conventions, lines exceeding the column width

+    in the patch above are split using a backslash character. The backslashes

+    at the end of a line and the white space at the beginning

+    of the following line are not part of the patch. A properly formatted patch

+    including the three changes above is available at

+    <eref target="http://jmvalin.ca/misc_stuff/opus_update.patch"/>.

     </t>

     </section>

@@ -215,8 +232,8 @@

       but when the output is downmixed to mono, the energy in the affected bands is cancelled

       sometimes resulting in audible artefacts.

       </t>

-      <t>A possible work-around for this issue would be to optionally allow the decoder to

-      not apply the 180-degree phase shift when the output is meant to be downmixed (inside or

+      <t>As a work-around for this issue, the decoder MAY choose not to apply the 180-degree

+      phase shift when the output is meant to be downmixed (inside or

       outside of the decoder).

       </t>

     </section>